© 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. 13405
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to speech and communication challenges

    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
    156
    +0.21
    1.2%
    466
    +0.13
    0.7%
    164
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.21
    0.02
    426
    +0.13
    0.02
    365
    +0.12
    0.02
    Negative Logits
    ¸
    -3.28
    ľĵ
    -3.19
    ·
    -2.88
    ĥ½
    -2.86
    ·¸
    -2.85
    Ĥ
    -2.75
    µ
    -2.69
    IJ
    -2.68
    Į
    -2.67
    <|outofrange|>
    -2.64
    POSITIVE LOGITS
    scape
    2.20
    less
    2.10
     uttered
    1.77
     goodbye
    1.70
    writer
    1.66
     language
    1.65
    go
    1.60
    blower
    1.59
    writers
    1.54
     sounded
    1.53
    Activations Density 0.186%

    No Known Activations