© 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. 29868
    Prev
    Next
    INDEX
    Explanations

    information related to user account management and access

    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
    187
    +0.13
    0.7%
    369
    +0.11
    0.6%
    199
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.13
    0.04
    189
    +0.11
    0.04
    398
    +0.10
    0.06
    Negative Logits
    CUSSION
    -1.77
    isms
    -1.54
    ')\
    -1.54
    CMC
    -1.52
    canonical
    -1.52
    '"
    -1.51
    asic
    -1.48
    ~(
    -1.48
     commens
    -1.47
    critical
    -1.47
    POSITIVE LOGITS
    ½
    2.32
    ¼
    2.25
    ↵
    2.18
    ↵
    2.18
    č↵
    2.18
    ↵↵↵
    2.18
    <|outofrange|>
    2.18
    <|outofrange|>
    2.18
    2.18
    2.18
    Activations Density 1.872%

    No Known Activations