© 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. 4-RES-SM
    11. 9575
    Prev
    Next
    INDEX
    Explanations

    the structure and organization of XML-related elements in documents

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.25
    1.5%
    375
    +0.14
    0.8%
    224
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.25
    0.01
    78
    +0.14
    0.00
    255
    +0.13
    0.00
    Negative Logits
    tons
    -1.67
    tail
    -1.65
    chers
    -1.51
    hers
    -1.49
     hypotheses
    -1.48
    uates
    -1.47
    atrix
    -1.46
    npmjs
    -1.37
    agogue
    -1.37
    hay
    -1.31
    POSITIVE LOGITS
    ª
    3.35
    µ
    3.30
    §
    3.25
    Ķ
    3.11
    ·
    3.11
    ļ
    3.10
    ĥ½
    2.96
    Ĵ
    2.88
    į
    2.86
    Ń
    2.84
    Activations Density 0.047%

    No Known Activations