Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40174
    Prev
    Next
    INDEX
    Explanations

    information related to deep ocean diving and underwater exploration

    oai_token-act-pair · gpt-3.5-turbo

    words associated with vertical positioning or movement, particularly focusing on high or deep locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    474
    +0.10
    0.5%
    570
    +0.09
    0.4%
    678
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.10
    0.10
    678
    +0.09
    0.08
    268
    +0.09
    0.03
    Negative Logits
    女
    -0.83
    advertising
    -0.73
    FG
    -0.68
    ussy
    -0.64
    onite
    -0.64
    abis
    -0.61
    Cola
    -0.61
    lez
    -0.61
     Parenthood
    -0.61
    çīĪ
    -0.60
    POSITIVE LOGITS
     cliffs
    0.91
     caves
    0.89
     depths
    0.89
    planes
    0.85
     altitude
    0.84
     canyon
    0.81
     ridge
    0.79
     airst
    0.76
     rocky
    0.75
     valleys
    0.74
    Activations Density 9.252%

    No Known Activations