© 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. 28767
    Prev
    Next
    INDEX
    Explanations

    system commands related to file management

    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
    156
    +0.19
    1.0%
    95
    +0.13
    0.7%
    139
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.19
    0.00
    148
    +0.13
    0.00
    53
    +0.12
    0.07
    Negative Logits
    ĥ½
    -1.82
    Ĭ
    -1.82
    ĵ
    -1.81
    ¨
    -1.80
    Ł
    -1.76
    §
    -1.72
    ª
    -1.70
    ij
    -1.70
    ¸
    -1.69
    ķ
    -1.66
    POSITIVE LOGITS
     files
    2.44
     directories
    2.22
    ename
    2.07
     filename
    2.01
    zilla
    1.98
     "$(
    1.96
     file
    1.89
     "$
    1.88
     directory
    1.83
    directory
    1.81
    Activations Density 0.976%

    No Known Activations