© 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. 25984
    Prev
    Next
    INDEX
    Explanations

    specific patterns or sequences in alphanumeric characters or code

    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
    59
    +0.13
    0.7%
    153
    +0.11
    0.6%
    387
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.13
    -0.00
    153
    +0.11
    0.14
    165
    +0.11
    0.07
    Negative Logits
    à«ĩ
    -2.19
    áĢ¬
    -1.48
    à«
    -1.39
    ED
    -1.29
     sig
    -1.29
    ding
    -1.29
    isd
    -1.28
    imgur
    -1.27
    chan
    -1.27
    earing
    -1.26
    POSITIVE LOGITS
    ®
    1.50
    achus
    1.49
    theless
    1.47
    lotte
    1.40
    eton
    1.36
    rice
    1.35
    ctrine
    1.31
     alike
    1.31
     ":
    1.31
    innati
    1.29
    Activations Density 2.606%

    No Known Activations