© 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. 4106
    Prev
    Next
    INDEX
    Explanations

    historical events and figures

    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
    +0.19
    0.8%
    659
    +0.13
    0.6%
    543
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.19
    0.23
    232
    +0.13
    0.17
    443
    +0.11
    0.09
    Negative Logits
     locker
    -0.80
     TBD
    -0.80
    itivity
    -0.80
     crunch
    -0.79
     takeaway
    -0.79
     feedback
    -0.79
     NFC
    -0.78
    Sensor
    -0.76
    ourcing
    -0.76
     inputs
    -0.76
    POSITIVE LOGITS
     XVI
    1.27
     Augustus
    1.23
     VIII
    1.20
     XIV
    1.14
     Galile
    1.14
     XII
    1.14
     ibn
    1.13
     Emperor
    1.12
     Napoleon
    1.11
     Carth
    1.10
    Activations Density 9.554%

    No Known Activations