© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27862
    Prev
    Next
    INDEX
    Explanations

    usage of the word "append" in various contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    148
    +0.15
    0.9%
    376
    +0.13
    0.7%
    225
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.15
    0.01
    148
    +0.13
    0.01
    139
    +0.13
    0.02
    Negative Logits
    ி
    -1.57
    degree
    -1.54
     own
    -1.51
    த
    -1.50
    ¯
    -1.47
    à¯
    -1.47
    ATER
    -1.46
     Conduct
    -1.45
     Own
    -1.45
    openh
    -1.45
    POSITIVE LOGITS
    eners
    1.90
    icul
    1.66
     recordings
    1.63
    ectomy
    1.60
    gery
    1.53
    ulous
    1.50
    itories
    1.50
     warning
    1.47
    resse
    1.45
     ears
    1.43
    Activations Density 0.152%

    No Known Activations