© 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. 4-RES-SM
    11. 14176
    Prev
    Next
    INDEX
    Explanations

    phrases inviting interaction and contributions from the audience

    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
    307
    +0.33
    1.9%
    306
    +0.18
    1.1%
    176
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.33
    0.15
    176
    +0.18
    0.14
    306
    +0.11
    0.08
    Negative Logits
    ·¸
    -2.25
    ij
    -2.02
    ¯
    -1.87
    ubicin
    -1.84
    ´
    -1.80
    İ
    -1.79
    ĥ
    -1.71
    Ŀ
    -1.71
    ŀ
    -1.63
    »¿
    -1.61
    POSITIVE LOGITS
     your
    4.05
     yourself
    3.63
     yours
    3.27
     yourselves
    3.24
    your
    3.15
     YOUR
    2.94
     Your
    2.89
     you
    2.88
    Your
    2.53
     YOU
    2.37
    Activations Density 1.850%

    No Known Activations