© 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. 29050
    Prev
    Next
    INDEX
    Explanations

    repeated occurrences of the suffix "der"

    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
    369
    +0.10
    0.6%
    10
    +0.10
    0.6%
    140
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.10
    0.02
    59
    +0.10
    0.02
    307
    +0.10
    0.02
    Negative Logits
    ¤
    -2.80
    Ī
    -2.63
    į
    -2.59
    ¿½
    -2.59
    Ĭ
    -2.57
    ·¸
    -2.50
    Į
    -2.35
    £
    -2.33
    ´
    -2.30
    Īĺ
    -2.29
    POSITIVE LOGITS
    ivation
    2.23
    ive
    2.05
    horn
    1.88
    rained
    1.79
    bent
    1.78
    ringer
    1.76
    naire
    1.76
    iving
    1.73
    ophers
    1.72
    ivable
    1.72
    Activations Density 0.138%

    No Known Activations