© 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. 13760
    Prev
    Next
    INDEX
    Explanations

    descriptors of physical appearance and attributes associated with individuals

    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
    466
    +0.20
    1.1%
    307
    +0.17
    1.0%
    231
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.20
    0.15
    204
    +0.17
    0.08
    56
    +0.12
    0.04
    Negative Logits
    ī
    -2.69
    ł
    -2.69
    Ħ
    -2.67
    -2.59
            ↵
    -2.59
    <|outofrange|>
    -2.59
    -2.59
    -2.59
    -2.59
        ↵
    -2.59
    POSITIVE LOGITS
     temperament
    3.08
     traits
    2.81
     personality
    2.80
     qualities
    2.77
     skills
    2.65
     beard
    2.51
     stature
    2.44
     skill
    2.44
     instincts
    2.41
     abilities
    2.38
    Activations Density 3.251%

    No Known Activations