© 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. 28283
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their relationships to 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
    63
    +0.15
    0.9%
    444
    +0.14
    0.8%
    179
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.15
    0.15
    410
    +0.14
    0.16
    191
    +0.13
    0.11
    Negative Logits
    ģ
    -2.14
    »
    -2.06
    Ĥ¬
    -2.05
    Ĥ
    -2.00
    ĸ
    -2.00
    ¿½
    -1.95
    ħ
    -1.95
    Ģ
    -1.94
    Ľ
    -1.94
    Ħ
    -1.83
    POSITIVE LOGITS
    )–
    1.51
    ?).
    1.51
    iani
    1.48
    ?)
    1.47
     Ranch
    1.39
    hurst
    1.39
    )—
    1.38
    stood
    1.38
    ères
    1.37
    strom
    1.37
    Activations Density 3.046%

    No Known Activations