© 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. 14240
    Prev
    Next
    INDEX
    Explanations

    character strings used as delimiters or symbols in programming code

    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
    156
    +0.16
    0.9%
    271
    +0.13
    0.7%
    272
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.16
    0.04
    36
    +0.13
    0.06
    203
    +0.12
    0.03
    Negative Logits
     centers
    -1.63
     presence
    -1.62
     Âĵ
    -1.48
     FIGS
    -1.45
     (“
    -1.42
     center
    -1.39
    ieurs
    -1.39
    eanor
    -1.38
    nikov
    -1.37
     basis
    -1.36
    POSITIVE LOGITS
    ·¸
    4.31
    ¿½
    4.15
    Ĩ
    4.13
    »
    4.04
    ½
    3.97
    ·
    3.88
    ľĵ
    3.88
    <|endoftext|>
    3.84
    ¦
    3.84
    ĭ
    3.83
    Activations Density 0.281%

    No Known Activations