© 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. 11262
    Prev
    Next
    INDEX
    Explanations

    annotations that indicate authorship and documentation metadata

    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
    410
    +0.17
    1.0%
    369
    +0.15
    0.9%
    419
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.17
    0.03
    143
    +0.15
    0.03
    379
    +0.12
    0.05
    Negative Logits
    orph
    -1.61
    irl
    -1.56
    )].
    -1.51
    tery
    -1.51
    istor
    -1.47
    sit
    -1.45
    tion
    -1.43
    iences
    -1.43
    orems
    -1.40
    .";
    -1.39
    POSITIVE LOGITS
    2.45
    ↵
    2.45
    ↵
    2.45
    ↵    ↵
    2.45
    ↵↵↵
    2.45
    2.45
    ↵
    2.45
    ↵
    2.45
     ↵
    2.45
    ↵↵
    2.45
    Activations Density 0.284%

    No Known Activations