© 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. 29407
    Prev
    Next
    INDEX
    Explanations

    verbs associated with actions taken by organizations or individuals in a formal context

    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
    153
    +0.16
    0.9%
    317
    +0.12
    0.7%
    23
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    462
    +0.16
    0.06
    474
    +0.12
    0.08
    148
    +0.11
    0.05
    Negative Logits
     quo
    -1.57
    acho
    -1.48
    arter
    -1.41
    lection
    -1.41
    ened
    -1.40
     inhibitors
    -1.37
    offe
    -1.36
    dried
    -1.35
    «
    -1.35
    rote
    -1.31
    POSITIVE LOGITS
    ĻĤ
    2.23
    pling
    1.64
    ging
    1.54
     minors
    1.45
    č↵
    1.44
    <|outofrange|>
    1.44
    č↵
    1.44
    ↵
    1.44
    1.44
    1.44
    Activations Density 1.091%

    No Known Activations