© 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. 10486
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "d" and their associated punctuation within the text

    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
    78
    +0.18
    1.0%
    468
    +0.16
    0.9%
    333
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.18
    0.05
    248
    +0.16
    0.03
    333
    +0.13
    0.03
    Negative Logits
    hered
    -1.55
    band
    -1.47
    chen
    -1.46
    lessly
    -1.45
    kin
    -1.43
     hands
    -1.42
     basis
    -1.42
     proper
    -1.42
    pec
    -1.40
     cost
    -1.40
    POSITIVE LOGITS
    ĥ
    2.19
    ģ
    2.05
    Į
    2.01
    IJ
    1.88
    ħ
    1.87
    ¦
    1.83
    Ī
    1.81
    Ļ
    1.78
    ĵ
    1.75
    Ĩ
    1.75
    Activations Density 0.086%

    No Known Activations