© 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. 11420
    Prev
    Next
    INDEX
    Explanations

    terms related to the consequences of actions or events

    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
    122
    +0.12
    0.7%
    268
    +0.12
    0.7%
    43
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    485
    +0.12
    0.02
    268
    +0.12
    0.03
    239
    +0.11
    0.02
    Negative Logits
    ĻĤ
    -2.50
    ²
    -2.46
    Īĺ
    -2.26
    ¿
    -2.25
    ´
    -2.25
    Ĥ
    -2.18
    ĸ´
    -2.17
    Ľ
    -2.13
    ¿½
    -2.12
    ¨
    -2.09
    POSITIVE LOGITS
    points
    1.82
    fulness
    1.68
    ableness
    1.66
    hole
    1.64
    ivity
    1.61
    ors
    1.61
     reduction
    1.61
    over
    1.60
    stones
    1.56
    ful
    1.55
    Activations Density 0.114%

    No Known Activations