© 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. 1-RES-SM
    11. 27625
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word 'GO' in various 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/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
    +0.17
    1.0%
    420
    +0.12
    0.6%
    356
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.17
    0.06
    48
    +0.12
    0.06
    81
    +0.11
    0.04
    Negative Logits
     morn
    -1.51
     spring
    -1.40
     downtown
    -1.39
     KO
    -1.39
     dusk
    -1.36
    ippy
    -1.34
     slow
    -1.33
    closed
    -1.32
     breeze
    -1.31
    MHz
    -1.31
    POSITIVE LOGITS
    ĻĤ
    2.02
    <|outofrange|>
    2.00
     ↵
    2.00
    2.00
    ↵
    2.00
    2.00
    č↵
    2.00
    <|outofrange|>
    2.00
    ↵↵
    2.00
    2.00
    Activations Density 1.750%

    No Known Activations