© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 34790
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to electronic devices

    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
    393
    +0.10
    0.7%
    127
    +0.07
    0.5%
    408
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.21
    393
    +0.07
    0.28
    636
    +0.07
    0.13
    Negative Logits
    ADRA
    -0.46
    achus
    -0.45
    gov
    -0.42
     acknowledges
    -0.42
    aling
    -0.41
     Aware
    -0.41
    itled
    -0.40
    fram
    -0.40
     Audit
    -0.39
    armed
    -0.39
    POSITIVE LOGITS
     uneven
    0.45
     brunt
    0.44
     stride
    0.42
     havoc
    0.41
     electrons
    0.40
     steam
    0.40
     disparate
    0.40
     retina
    0.40
     landfill
    0.40
     toll
    0.39
    Activations Density 10.029%

    No Known Activations