© 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. 9373
    Prev
    Next
    INDEX
    Explanations

    URL query parameters

    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
    +0.19
    1.0%
    103
    +0.14
    0.7%
    461
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.19
    0.02
    103
    +0.14
    0.02
    175
    +0.11
    0.01
    Negative Logits
    ienne
    -1.64
     excess
    -1.51
    istically
    -1.47
    ians
    -1.46
    anger
    -1.46
     alive
    -1.45
    [@
    -1.45
     [@
    -1.45
    liers
    -1.44
     (\>
    -1.42
    POSITIVE LOGITS
    keywords
    2.01
    ¸
    1.93
    >&
    1.90
    topic
    1.89
    ¬
    1.84
    ¾
    1.80
    Ģ
    1.80
    sid
    1.77
    ŀ
    1.76
    amsbsy
    1.75
    Activations Density 0.180%

    No Known Activations