© 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. 31141
    Prev
    Next
    INDEX
    Explanations

    references to job-related qualifications and positions

    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
    271
    +0.19
    1.1%
    320
    +0.17
    1.0%
    218
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.19
    0.10
    34
    +0.17
    0.14
    78
    +0.15
    0.04
    Negative Logits
     (<
    -1.58
    .$$
    -1.54
    ).$$
    -1.50
    >).
    -1.48
     strips
    -1.44
     corresponding
    -1.40
    $;
    -1.39
    ),$$
    -1.39
    ).
    -1.38
    \}.$$
    -1.38
    POSITIVE LOGITS
    į
    2.56
    Ļª
    2.54
    «
    2.27
    ¥
    2.21
    ¸
    2.19
    İ
    2.12
    Ń
    2.07
    ĭ
    2.02
    Į
    2.01
    ĥ
    1.96
    Activations Density 4.289%

    No Known Activations