© 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. 29220
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "report" and related terms in a variety of 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/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
    23
    +0.19
    1.1%
    365
    +0.13
    0.8%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.19
    0.02
    511
    +0.13
    0.01
    356
    +0.13
    0.01
    Negative Logits
    »
    -2.62
    ĭ
    -2.52
    ®
    -2.40
    IJ
    -2.33
    §
    -2.30
    ¯
    -2.30
    ¬
    -2.25
    ī
    -2.22
    Ĵ
    -2.14
    ¹
    -2.08
    POSITIVE LOGITS
    beit
    1.65
    head
    1.65
    atively
    1.58
    cule
    1.56
    urate
    1.52
    imony
    1.51
     disappointing
    1.51
    ulate
    1.50
     mention
    1.45
    atory
    1.45
    Activations Density 0.040%

    No Known Activations