© 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. 2-RES-SM
    11. 31052
    Prev
    Next
    INDEX
    Explanations

    HTML tags and content related to web structure

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    333
    +0.13
    0.8%
    167
    +0.12
    0.7%
    31
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.13
    0.08
    140
    +0.12
    0.09
    333
    +0.12
    0.07
    Negative Logits
    Ļª
    -2.62
    IJ
    -2.25
    »¿
    -2.16
    ľĵ
    -2.16
    ¨
    -2.06
    Ī
    -2.05
    ĸ
    -2.04
    Ń
    -2.02
    ŀ
    -1.95
    Ĭ
    -1.95
    POSITIVE LOGITS
    __.
    1.69
    >;
    1.65
    .**
    1.62
    ?**
    1.55
    ."_
    1.53
    NESS
    1.51
    holds
    1.50
     kin
    1.46
    ”;
    1.45
     withheld
    1.42
    Activations Density 5.305%

    No Known Activations