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. 4050
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of reducing or cutting back on something

    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
    447
    +0.26
    1.1%
    624
    +0.12
    0.5%
    421
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.26
    0.12
    375
    +0.12
    0.05
    608
    +0.10
    0.14
    Negative Logits
    Found
    -0.72
    old
    -0.68
    ¯¯
    -0.68
    new
    -0.67
    rod
    -0.67
    Bet
    -0.64
    REL
    -0.63
    finished
    -0.63
    Gener
    -0.63
    place
    -0.62
    POSITIVE LOGITS
     inhib
    0.84
    icides
    0.79
    xual
    0.79
    uce
    0.78
     sidx
    0.78
     observable
    0.77
     regress
    0.77
    ħĭ
    0.77
     emissions
    0.76
     dioxide
    0.74
    Activations Density 10.197%

    No Known Activations