© 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. 1-RES-SM
    11. 29100
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "hear" and its variations

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    246
    +0.12
    0.7%
    376
    +0.12
    0.7%
    192
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.12
    0.03
    192
    +0.12
    0.03
    246
    +0.12
    0.03
    Negative Logits
    µ
    -2.44
    ·¸
    -2.19
    »¿
    -2.18
    ¤
    -2.16
    Ŀ
    -2.15
    ĩ
    -2.04
    IJ
    -2.02
    Ń
    -2.00
    ¸
    -1.98
    ľĵ
    -1.97
    POSITIVE LOGITS
     noises
    1.83
     sound
    1.62
     About
    1.58
     singing
    1.58
     noise
    1.56
     msgid
    1.55
    raid
    1.54
     sounds
    1.53
     buzz
    1.52
     screams
    1.51
    Activations Density 0.243%

    No Known Activations