© 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. 25500
    Prev
    Next
    INDEX
    Explanations

    references to staff and personnel in various 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
    156
    +0.18
    1.0%
    365
    +0.16
    0.9%
    172
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.18
    0.04
    172
    +0.16
    0.02
    437
    +0.13
    0.03
    Negative Logits
    §
    -2.62
    ¿½
    -2.44
    ı
    -2.34
    ĵ
    -2.29
    ĥ
    -2.22
    ↵↵↵
    -2.19
    <|outofrange|>
    -2.19
    ↵
    -2.19
    ↵
    -2.19
    ↵
    -2.19
    POSITIVE LOGITS
    ership
    1.95
    member
    1.87
    ing
    1.86
    members
    1.81
    ycin
    1.76
    ICU
    1.74
    erad
    1.73
    manager
    1.72
    uri
    1.67
    house
    1.66
    Activations Density 0.172%

    No Known Activations