© 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. 25239
    Prev
    Next
    INDEX
    Explanations

    instances of the word "shows" and its variations indicating visual representation

    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
    23
    +0.23
    1.3%
    112
    +0.12
    0.7%
    72
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.23
    0.23
    156
    +0.12
    0.12
    271
    +0.12
    0.09
    Negative Logits
    ±
    -2.66
    IJ
    -2.44
    §
    -2.44
    į
    -2.15
    ĭ
    -2.09
    Ħ
    -2.07
    Ń
    -2.05
    İ
    -2.00
    \]\].
    -1.92
    ¼
    -1.92
    POSITIVE LOGITS
     how
    1.98
    how
    1.89
     fly
    1.79
    ational
    1.76
    ered
    1.76
    ering
    1.74
    matically
    1.73
     reason
    1.68
    hift
    1.66
    rapy
    1.63
    Activations Density 0.577%

    No Known Activations