© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 1473
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and politics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.18
    0.7%
    640
    +0.17
    0.7%
    123
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.18
    0.18
    29
    +0.17
    0.17
    22
    +0.14
    0.15
    Negative Logits
    soever
    -0.94
    terday
    -0.87
    catentry
    -0.84
    NOW
    -0.81
    casters
    -0.80
     learners
    -0.80
     lodged
    -0.78
     announ
    -0.75
     %%
    -0.74
    ¿½
    -0.73
    POSITIVE LOGITS
     favor
    1.44
     accordance
    1.40
     lieu
    1.37
     conjunction
    1.36
    humane
    1.35
     vain
    1.32
    ordinate
    1.31
    roads
    1.27
     unison
    1.26
    animate
    1.25
    Activations Density 2.122%

    No Known Activations