© 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. 1-RES-SM
    11. 28878
    Prev
    Next
    INDEX
    Explanations

    patterns related to numerical values and alphanumeric codes

    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
    98
    +0.15
    0.9%
    12
    +0.12
    0.7%
    271
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.15
    0.07
    12
    +0.12
    0.04
    168
    +0.11
    0.03
    Negative Logits
    Ł
    -3.19
    §
    -3.17
    ®
    -3.11
    ĸ
    -3.09
    ¾
    -3.07
    ħ
    -2.91
    ¦
    -2.91
    ĩ
    -2.90
    Ĭ
    -2.86
    ²
    -2.84
    POSITIVE LOGITS
     launched
    1.44
    osomal
    1.42
     Attorney
    1.39
     branch
    1.37
     released
    1.37
     prosecutor
    1.34
     Appeal
    1.34
     naked
    1.33
     searched
    1.33
    ãĤī
    1.32
    Activations Density 1.195%

    No Known Activations