© 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. 29280
    Prev
    Next
    INDEX
    Explanations

    references to aspects of measurement or quality

    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
    134
    +0.13
    0.7%
    412
    +0.11
    0.6%
    148
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.13
    0.04
    448
    +0.11
    0.04
    30
    +0.10
    0.04
    Negative Logits
    ONA
    -1.60
    omitempty
    -1.46
     responders
    -1.43
    TTP
    -1.38
    ubicin
    -1.38
     acceptance
    -1.36
    izumab
    -1.34
     pH
    -1.33
    ETHOD
    -1.32
     MHz
    -1.31
    POSITIVE LOGITS
    ¿½
    1.94
    ential
    1.72
    nings
    1.60
    ogly
    1.59
     parentheses
    1.55
    geries
    1.52
    encia
    1.50
    anuts
    1.46
    )?
    1.43
    ĻĤ
    1.41
    Activations Density 0.506%

    No Known Activations