© 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. 29566
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structural elements 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
    220
    +0.12
    0.6%
    467
    +0.10
    0.6%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.12
    0.00
    23
    +0.10
    0.00
    143
    +0.10
    0.00
    Negative Logits
    cheon
    -1.74
    ets
    -1.56
     ranked
    -1.48
    *](#
    -1.47
     cloning
    -1.45
    ight
    -1.42
    ifier
    -1.40
     sixth
    -1.40
     scoring
    -1.38
    pires
    -1.36
    POSITIVE LOGITS
    americ
    1.84
    rites
    1.50
    rios
    1.49
    ajas
    1.49
     beaches
    1.48
    agine
    1.46
    ız
    1.44
    destruct
    1.42
    selves
    1.42
    apk
    1.41
    Activations Density 0.001%

    No Known Activations