© 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. 10100
    Prev
    Next
    INDEX
    Explanations

    questions and discussions related to choice and decision-making

    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
    476
    +0.13
    0.7%
    398
    +0.11
    0.6%
    365
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.13
    0.07
    81
    +0.11
    0.03
    363
    +0.11
    0.04
    Negative Logits
    Ļª
    -2.92
    ij
    -2.31
    ĸ
    -2.30
    Ĵ
    -2.13
    Ĺ
    -2.10
    ¸
    -2.05
    ¯
    -2.04
    ĻĤ
    -2.04
    ³
    -2.02
    ĥ½
    -2.01
    POSITIVE LOGITS
    has
    2.88
     have
    2.83
    have
    2.83
     has
    2.62
     had
    2.32
     Have
    2.28
    Has
    2.14
    've
    2.13
    having
    2.08
     Has
    2.02
    Activations Density 0.623%

    No Known Activations