Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26844
    Prev
    Next
    INDEX
    Explanations

    references to software licenses

    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
    42
    +0.13
    0.8%
    251
    +0.11
    0.6%
    290
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    42
    +0.13
    0.02
    251
    +0.11
    0.02
    290
    +0.11
    0.02
    Negative Logits
    *](#
    -1.53
     departing
    -1.51
    than
    -1.44
    jo
    -1.43
    other
    -1.42
    UMP
    -1.41
    Affirmed
    -1.41
    CRE
    -1.39
     door
    -1.38
     doors
    -1.38
    POSITIVE LOGITS
    ropri
    1.74
    isans
    1.66
    igator
    1.52
    igated
    1.50
    ificate
    1.48
    edly
    1.48
     qual
    1.45
     sab
    1.44
    ivos
    1.44
    urities
    1.41
    Activations Density 0.031%

    No Known Activations