© 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. 31579
    Prev
    Next
    INDEX
    Explanations

    terms related to hair and its various aspects and treatments

    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
    156
    +0.20
    1.1%
    269
    +0.14
    0.8%
    314
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.20
    0.03
    173
    +0.14
    0.02
    56
    +0.12
    0.00
    Negative Logits
    č↵
    -2.92
    -2.92
     ↵
    -2.92
    <|outofrange|>
    -2.92
    ↵↵
    -2.92
    -2.92
    <|outofrange|>
    -2.92
    -2.92
    -2.92
    <|outofrange|>
    -2.92
    POSITIVE LOGITS
    pins
    2.27
    pin
    2.26
    balls
    2.20
    ball
    2.04
    walker
    1.96
    brush
    1.79
    bread
    1.69
    spray
    1.69
    flow
    1.66
    blower
    1.65
    Activations Density 0.139%

    No Known Activations