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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 9264
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax and structure in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    78
    +0.15
    0.8%
    21
    +0.14
    0.8%
    52
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.15
    0.08
    78
    +0.14
    0.01
    354
    +0.11
    0.09
    Negative Logits
    rapeut
    -1.66
    gado
    -1.54
    ento
    -1.51
    starter
    -1.51
    acting
    -1.51
    appropriate
    -1.51
     )"
    -1.41
    ,'"
    -1.33
    binding
    -1.33
     ]"
    -1.32
    POSITIVE LOGITS
    };
    2.55
    ŀ
    2.33
    ¤
    2.14
    Ĥ
    2.09
    ¡
    2.08
    Ĵ
    2.06
    ²
    2.06
    Īĺ
    2.01
    extern
    2.00
     typedef
    1.95
    Activations Density 0.623%

    No Known Activations