© 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. 13060
    Prev
    Next
    INDEX
    Explanations

    identifiers and keywords associated with programming and system configuration

    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
    419
    +0.17
    1.0%
    262
    +0.13
    0.7%
    218
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.17
    0.09
    482
    +0.13
    0.10
    352
    +0.12
    0.07
    Negative Logits
    ERTY
    -1.61
    aliana
    -1.49
    xsl
    -1.47
     include
    -1.44
    ://
    -1.44
     vener
    -1.42
    ographic
    -1.35
    lication
    -1.34
     difference
    -1.34
     flaw
    -1.33
    POSITIVE LOGITS
    ¿½
    1.97
    į
    1.78
    ¡
    1.72
    Ĵ
    1.66
    ¦
    1.60
    ´
    1.58
    Ĭ
    1.56
    Ŀ
    1.54
    Ħ
    1.53
    ¸
    1.52
    Activations Density 2.861%

    No Known Activations