© 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. 25137
    Prev
    Next
    INDEX
    Explanations

    references to agents and their attributes in a technical context

    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
    118
    +0.16
    0.9%
    18
    +0.13
    0.8%
    219
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.16
    0.03
    335
    +0.13
    0.03
    18
    +0.13
    0.04
    Negative Logits
    \)
    -1.59
     ")
    -1.48
    uded
    -1.44
     assim
    -1.41
     engineered
    -1.39
     collectively
    -1.37
     refractory
    -1.36
     done
    -1.33
     ester
    -1.32
     ?>
    -1.31
    POSITIVE LOGITS
    ½
    2.19
    ¾
    2.17
    İ
    2.15
    hood
    2.03
    Ĵ
    1.94
    ¶
    1.92
    ¼
    1.86
    lights
    1.86
    Ī
    1.76
    uses
    1.74
    Activations Density 0.384%

    No Known Activations