© 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. 4-RES-SM
    11. 11043
    Prev
    Next
    INDEX
    Explanations

    mentions of fandom or enthusiastic following

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.12
    0.7%
    358
    +0.12
    0.7%
    263
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.12
    0.03
    348
    +0.12
    0.02
    232
    +0.12
    0.02
    Negative Logits
     msgid
    -1.73
     PBX
    -1.65
    hift
    -1.54
     thereto
    -1.47
    Newton
    -1.44
    eer
    -1.42
     typeof
    -1.40
    typeof
    -1.39
    frast
    -1.39
    InstanceState
    -1.37
    POSITIVE LOGITS
    atics
    3.21
    atic
    2.95
    fare
    2.69
    fiction
    2.50
    atically
    2.44
    boys
    2.37
    boy
    2.31
    atism
    2.00
    base
    1.85
     favorite
    1.84
    Activations Density 0.410%

    No Known Activations