© 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. 26471
    Prev
    Next
    INDEX
    Explanations

    mathematical or numerical data presented in a structured format

    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
    326
    +0.22
    1.3%
    17
    +0.18
    1.0%
    274
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.22
    0.06
    149
    +0.18
    0.09
    439
    +0.11
    0.07
    Negative Logits
     diligence
    -1.48
    eration
    -1.45
    ;/
    -1.40
    lf
    -1.38
    metrics
    -1.37
     Heidegger
    -1.36
     KCl
    -1.35
     Reporting
    -1.33
    ^âĪĴ
    -1.32
    ainer
    -1.28
    POSITIVE LOGITS
    ĥ½
    2.10
     lands
    1.49
    ľĵ
    1.41
    »
    1.39
     District
    1.36
     deaths
    1.36
    onder
    1.33
    fecture
    1.30
    iscus
    1.29
    vous
    1.28
    Activations Density 3.311%

    No Known Activations