© 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. 29575
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "debut"

    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
    410
    +0.12
    0.6%
    156
    +0.11
    0.6%
    306
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.04
    156
    +0.11
    0.03
    271
    +0.11
    0.01
    Negative Logits
    ´
    -2.30
    ¿
    -2.29
    º
    -2.24
    °
    -2.15
    ĸ´
    -2.14
    ¸
    -2.14
    ³
    -2.06
    Ķ
    -2.04
    ¯
    -2.01
    Ħ
    -1.99
    POSITIVE LOGITS
    teen
    2.12
    atures
    1.64
    ember
    1.63
    antes
    1.56
    nant
    1.48
    LEX
    1.43
    orphic
    1.42
    opp
    1.41
    ream
    1.41
    antly
    1.41
    Activations Density 0.275%

    No Known Activations