© 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. 45759
    Prev
    Next
    INDEX
    Explanations

    details provided in a review about a specific product or object

    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
    87
    +0.43
    3.7%
    480
    +0.38
    3.2%
    266
    +0.21
    1.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.43
    0.09
    266
    +0.38
    0.54
    276
    +0.21
    0.28
    Negative Logits
     Rodham
    -0.51
     constitutional
    -0.51
    iberal
    -0.47
     Islamist
    -0.45
     ÂŃ
    -0.44
     Political
    -0.44
     Bashar
    -0.42
     congressional
    -0.42
     Osama
    -0.42
     Democratic
    -0.42
    POSITIVE LOGITS
     kinda
    0.57
     haha
    0.54
     devs
    0.52
     alot
    0.51
     ;)
    0.48
     HUGE
    0.48
     XD
    0.47
     somew
    0.47
     backend
    0.46
     :)
    0.44
    Activations Density 30.440%

    No Known Activations