© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 14571
    Prev
    Next
    INDEX
    Explanations

    the letter 'c' as a prominent feature

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.17
    1.0%
    78
    +0.14
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.17
    0.02
    148
    +0.14
    0.01
    311
    +0.12
    0.01
    Negative Logits
    e
    -1.80
    yon
    -1.62
    ĻĤ
    -1.54
    ei
    -1.51
     fulfilled
    -1.49
    s
    -1.47
    .’”
    -1.45
    ”;
    -1.44
    ker
    -1.43
    ”:
    -1.42
    POSITIVE LOGITS
     *)
    1.89
    ++)
    1.85
    )
    1.83
    __)
    1.76
    )](
    1.72
    opyright
    1.70
    ^)
    1.66
    )&
    1.65
    )^[@
    1.64
    )\
    1.63
    Activations Density 0.017%

    No Known Activations