© 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 EvalsExportsAPI 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. 27754
    Prev
    Next
    INDEX
    Explanations

    words ending in "ally"

    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
    68
    +0.11
    0.6%
    468
    +0.10
    0.6%
    276
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.04
    86
    +0.10
    0.04
    276
    +0.10
    0.03
    Negative Logits
    ·¸
    -2.72
    Ļ
    -2.42
    ļ
    -2.40
    Ķ
    -2.29
    Ĥ¬
    -2.19
    ½
    -2.17
    ¦
    -2.13
    ¯
    -2.12
    ¸
    -2.11
    ®
    -2.07
    POSITIVE LOGITS
    etic
    1.54
    vist
    1.51
    sis
    1.45
    mology
    1.44
    gian
    1.44
    nn
    1.43
    lation
    1.41
    mph
    1.40
     Wrote
    1.39
     speaking
    1.38
    Activations Density 0.209%

    No Known Activations