© 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. 2-RES-SM
    11. 29669
    Prev
    Next
    INDEX
    Explanations

    API-related calls and error messages

    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
    419
    +0.20
    1.1%
    135
    +0.18
    1.0%
    47
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    135
    +0.20
    0.16
    271
    +0.18
    -0.04
    480
    +0.15
    0.09
    Negative Logits
     safety
    -1.58
     career
    -1.47
    oken
    -1.36
     Safety
    -1.36
    fulness
    -1.36
    iquit
    -1.29
    iels
    -1.28
     jeopardy
    -1.28
     immunity
    -1.28
     realism
    -1.27
    POSITIVE LOGITS
    @
    1.84
    gets
    1.68
    #
    1.60
    #,
    1.56
    illary
    1.56
    cott
    1.50
    itte
    1.50
     brains
    1.43
    ubert
    1.42
    lette
    1.42
    Activations Density 4.325%

    No Known Activations