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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-SM
    6. 29064
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or names

    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
    356
    +0.15
    0.8%
    410
    +0.14
    0.8%
    350
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.15
    0.03
    338
    +0.14
    0.02
    350
    +0.12
    0.02
    Negative Logits
    boards
    -1.74
    board
    -1.65
    banks
    -1.56
    )](#
    -1.56
    strength
    -1.53
    blown
    -1.51
     entire
    -1.41
    ),$$
    -1.38
    boarding
    -1.36
    lando
    -1.36
    POSITIVE LOGITS
    ournal
    2.33
    º
    2.33
    ĻĤ
    2.19
    ¥
    2.13
    §
    2.12
    ¤
    2.11
    °
    2.02
    Ń
    1.95
    ³
    1.94
    ŀ
    1.93
    Activations Density 0.156%

    No Known Activations