© 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 EvalsExportsAPI 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. 27810
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly numerical values and formats

    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
    123
    +0.19
    1.1%
    221
    +0.13
    0.7%
    14
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.19
    0.12
    204
    +0.13
    0.12
    425
    +0.13
    0.10
    Negative Logits
    *,
    -1.46
    `:
    -1.45
    ķ
    -1.39
     ****
    -1.33
     ***
    -1.30
    anie
    -1.30
     protected
    -1.30
    rangle
    -1.30
     inactivated
    -1.28
     shall
    -1.25
    POSITIVE LOGITS
    osterone
    1.67
    lli
    1.59
     herself
    1.58
    terior
    1.52
    lotte
    1.46
    journals
    1.46
    ationally
    1.43
    itrile
    1.42
    years
    1.36
    CLUS
    1.35
    Activations Density 2.663%

    No Known Activations