© 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. 26938
    Prev
    Next
    INDEX
    Explanations

    instances of the word "form" in various contexts

    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
    93
    +0.13
    0.7%
    389
    +0.13
    0.7%
    267
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.13
    0.03
    93
    +0.13
    0.02
    267
    +0.12
    0.02
    Negative Logits
    ĻĤ
    -2.15
    woke
    -2.03
    unnumbered
    -1.80
    sburg
    -1.59
    omitempty
    -1.47
    sell
    -1.45
     bitch
    -1.44
    ľĵ
    -1.42
    ·
    -1.37
     Shannon
    -1.32
    POSITIVE LOGITS
    ulating
    2.61
    idable
    2.60
    ative
    2.33
    icum
    2.04
    ics
    2.00
    ulas
    1.93
    als
    1.89
    atics
    1.88
    emic
    1.83
    ulator
    1.79
    Activations Density 0.052%

    No Known Activations