© 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. 2-RES-SM
    11. 13076
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases associated with legal or regulatory context

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    31
    +0.13
    0.7%
    213
    +0.11
    0.6%
    294
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.13
    0.07
    187
    +0.11
    0.05
    168
    +0.10
    0.06
    Negative Logits
    "}](#
    -1.63
    -->
    -1.60
    blockList
    -1.56
    cdots
    -1.39
    static
    -1.38
    ostream
    -1.38
    cyclic
    -1.36
     msgid
    -1.35
     electrophoresis
    -1.33
    CIT
    -1.33
    POSITIVE LOGITS
    Īĺ
    2.36
    ·
    2.17
    Ķ
    2.02
    »¿
    1.96
    ľ
    1.95
    Į
    1.76
    ĥ
    1.76
    Ĥ¬
    1.76
    ¸
    1.71
    Ĭ
    1.71
    Activations Density 1.858%

    No Known Activations