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. 33420
    Prev
    Next
    INDEX
    Explanations

    statistical data and information related to various political, social, and economic topics

    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%
    393
    +0.13
    0.6%
    172
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.26
    0.06
    262
    +0.13
    0.05
    294
    +0.11
    0.04
    Negative Logits
    aer
    -0.84
    iotic
    -0.84
    hack
    -0.81
    elle
    -0.77
    illet
    -0.77
    iot
    -0.77
    ophys
    -0.76
    atter
    -0.75
    entry
    -0.74
    opath
    -0.74
    POSITIVE LOGITS
     retaining
    0.98
     maintaining
    0.96
     ignoring
    0.91
     browsing
    0.90
     simultaneously
    0.87
     preserving
    0.84
     others
    0.82
     awaiting
    0.81
     keeping
    0.80
     avoiding
    0.80
    Activations Density 5.213%

    No Known Activations