© 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. 2-RES-SM
    11. 27960
    Prev
    Next
    INDEX
    Explanations

    mentions of user interface buttons in technical contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    156
    +0.18
    1.0%
    287
    +0.12
    0.7%
    99
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.18
    0.03
    99
    +0.12
    0.02
    134
    +0.12
    0.02
    Negative Logits
     borough
    -1.57
    ieurs
    -1.44
    7554
    -1.42
    yr
    -1.41
     facult
    -1.40
    ithe
    -1.39
     society
    -1.37
     suburbs
    -1.35
     COURT
    -1.35
     Minor
    -1.34
    POSITIVE LOGITS
    picker
    1.87
    press
    1.81
     presses
    1.79
     pressed
    1.76
    face
    1.76
    backs
    1.69
    pressed
    1.68
    smith
    1.65
    button
    1.64
    bind
    1.62
    Activations Density 0.168%

    No Known Activations