© 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. 4-RES-SM
    11. 12817
    Prev
    Next
    INDEX
    Explanations

    phrases involving abusive or violent sexual behavior

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.21
    1.3%
    445
    +0.12
    0.7%
    430
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.21
    0.03
    78
    +0.12
    -0.04
    137
    +0.11
    0.09
    Negative Logits
     Species
    -1.57
     genus
    -1.56
    estock
    -1.55
     antifungal
    -1.50
    otoxin
    -1.48
    Canada
    -1.47
    env
    -1.44
    UV
    -1.43
    species
    -1.43
    Azure
    -1.42
    POSITIVE LOGITS
     tempo
    1.64
     sessions
    1.59
     climax
    1.51
     unanimous
    1.50
     maneuver
    1.49
     convolution
    1.40
     maneu
    1.40
     streets
    1.39
     Sessions
    1.39
     repetitions
    1.39
    Activations Density 1.576%

    No Known Activations