© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28741
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce research findings or reports

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    466
    +0.13
    0.7%
    321
    +0.12
    0.6%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.13
    0.04
    404
    +0.12
    0.04
    176
    +0.11
    0.04
    Negative Logits
    gs
    -1.54
    gio
    -1.44
     (.
    -1.37
    thing
    -1.34
    hler
    -1.33
     himself
    -1.31
     resuspended
    -1.26
    acer
    -1.26
    ersion
    -1.26
    bits
    -1.25
    POSITIVE LOGITS
    ĻĤ
    3.03
    ĥ½
    2.84
    ↵
    2.82
    ↵↵
    2.82
           ↵
    2.82
    <|outofrange|>
    2.82
    ↵
    2.82
    <|outofrange|>
    2.82
    ↵
    2.82
    ↵  ³³³
    2.82
    Activations Density 0.220%

    No Known Activations