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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 33389
    Prev
    Next
    INDEX
    Explanations

    words related to nobility and ranks, as well as specific names

    oai_token-act-pair · gpt-3.5-turbo
    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
    685
    +0.10
    0.6%
    692
    +0.09
    0.5%
    313
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.24
    61
    +0.09
    0.08
    656
    +0.08
    0.07
    Negative Logits
    utic
    -0.71
    Downloadha
    -0.67
    izable
    -0.62
    isers
    -0.61
    ization
    -0.59
     Nadu
    -0.58
    icago
    -0.57
     ultras
    -0.57
    Ñı
    -0.57
    è¦ļéĨĴ
    -0.55
    POSITIVE LOGITS
    minded
    0.76
    bridge
    0.75
    Nob
    0.74
    doms
    0.67
    odies
    0.66
     bour
    0.62
    rants
    0.61
    bour
    0.61
    rie
    0.61
    bors
    0.60
    Activations Density 9.862%

    No Known Activations