© 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. 28563
    Prev
    Next
    INDEX
    Explanations

    references to shooting incidents

    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
    358
    +0.17
    1.0%
    164
    +0.12
    0.7%
    490
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.17
    0.02
    358
    +0.12
    0.03
    134
    +0.11
    0.02
    Negative Logits
    ľĵ
    -3.93
    ŀ
    -3.81
    ļ
    -3.72
    ĭ
    -3.71
    ķ
    -3.68
    ¶
    -3.63
    §
    -3.63
    ĥ½
    -3.58
    °
    -3.56
    ·¸
    -3.55
    POSITIVE LOGITS
    guns
    3.28
    gun
    2.46
    oslav
    2.00
    shots
    1.91
    nikov
    1.84
    outs
    1.73
    ogue
    1.66
     fired
    1.66
     Vict
    1.60
     blast
    1.58
    Activations Density 0.237%

    No Known Activations