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. 45563
    Prev
    Next
    INDEX
    Explanations

    political and economic terms or contexts

    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
    +0.37
    2.2%
    481
    +0.11
    0.6%
    435
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.37
    0.27
    184
    +0.11
    0.08
    641
    +0.09
    0.18
    Negative Logits
    Downloadha
    -0.58
     allegedly
    -0.45
    adh
    -0.44
     dared
    -0.44
     supposedly
    -0.43
     guiActiveUn
    -0.43
     ruining
    -0.43
     Paste
    -0.42
    >>\
    -0.41
     recently
    -0.41
    POSITIVE LOGITS
     oneself
    0.73
     ourselves
    0.72
    cipled
    0.60
     anew
    0.57
     yourself
    0.54
     yourselves
    0.54
     sacrific
    0.53
     meaningful
    0.52
    ardless
    0.51
     humility
    0.49
    Activations Density 19.095%

    No Known Activations