© 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. 26362
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial assessments or evaluations

    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
    31
    +0.12
    0.7%
    265
    +0.11
    0.6%
    141
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.10
    478
    +0.11
    -0.01
    78
    +0.11
    0.06
    Negative Logits
    iforn
    -1.61
    idone
    -1.48
    dav
    -1.42
    irl
    -1.39
    watson
    -1.32
    rimin
    -1.31
    dden
    -1.30
    ['
    -1.28
    wat
    -1.26
    elesc
    -1.25
    POSITIVE LOGITS
    «
    2.15
    ĥ½
    2.03
    ¬
    1.99
    "?"
    1.94
    Ľ
    1.83
    ¯
    1.75
    ¢
    1.74
    ķ
    1.74
    ¶
    1.68
    ¹
    1.66
    Activations Density 2.427%

    No Known Activations