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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 26989
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Safer."

    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
    369
    +0.21
    1.2%
    144
    +0.14
    0.8%
    323
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.21
    0.02
    369
    +0.14
    0.02
    241
    +0.13
    0.02
    Negative Logits
    tons
    -2.35
    MENT
    -1.98
    nant
    -1.74
    wise
    -1.68
    sime
    -1.67
    MENTS
    -1.67
    t
    -1.59
    ANC
    -1.53
    mente
    -1.53
    ontally
    -1.52
    POSITIVE LOGITS
    unders
    1.67
    ÅĨ
    1.64
    ³
    1.60
    ÅĽci
    1.55
    zerba
    1.52
    pere
    1.49
    quel
    1.47
    iat
    1.43
    iale
    1.42
    uri
    1.41
    Activations Density 0.095%

    No Known Activations