© 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. 1-RES-SM
    11. 24884
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values in text

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    287
    +0.16
    0.9%
    156
    +0.13
    0.7%
    262
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.16
    0.03
    262
    +0.13
    0.03
    195
    +0.13
    0.02
    Negative Logits
    ĥ½
    -4.44
    ľĵ
    -4.40
    ½
    -4.38
    §
    -4.34
    ¿
    -4.32
    -4.30
    -4.30
    ↵
    -4.30
    ↵
    -4.30
    <|outofrange|>
    -4.30
    POSITIVE LOGITS
    hoe
    2.17
    cript
    2.12
    heet
    2.09
    pace
    1.91
    paces
    1.88
    hell
    1.81
    ymbol
    1.79
    mith
    1.77
    quare
    1.72
    ource
    1.67
    Activations Density 0.113%

    No Known Activations