© 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. 14677
    Prev
    Next
    INDEX
    Explanations

    patterns in web-related technical information or code references

    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
    156
    +0.16
    0.9%
    291
    +0.14
    0.8%
    41
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.16
    0.06
    238
    +0.14
    0.01
    500
    +0.11
    0.04
    Negative Logits
    ĻĤ
    -3.19
    ħ
    -3.14
    -2.90
          ↵
    -2.90
    -2.90
    <|outofrange|>
    -2.90
    -2.90
    ↵        ↵
    -2.90
    ↵  âĢĥ
    -2.90
    -2.90
    POSITIVE LOGITS
    &
    4.16
    .&
    3.21
    ,&
    3.12
    >&
    2.96
    =&
    2.95
    }&
    2.79
    &$
    2.75
    %
    2.73
    ">"
    2.61
    ?_
    2.53
    Activations Density 0.763%

    No Known Activations