© 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. 29270
    Prev
    Next
    INDEX
    Explanations

    references to function arguments

    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
    184
    +0.15
    0.8%
    376
    +0.14
    0.8%
    250
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.15
    0.03
    86
    +0.14
    0.03
    184
    +0.13
    0.03
    Negative Logits
    ľĵ
    -3.97
    ĥ½
    -3.84
    º
    -3.71
    ·¸
    -3.69
    ĻĤ
    -3.60
    ¿½
    -3.54
    ĥ
    -3.52
    ´
    -3.38
    ·
    -3.36
    »¿
    -3.30
    POSITIVE LOGITS
    orted
    1.69
    paced
    1.64
     crate
    1.58
    set
    1.53
     ration
    1.50
    aurus
    1.46
    CRIPT
    1.45
     set
    1.45
     knob
    1.44
    plit
    1.41
    Activations Density 0.216%

    No Known Activations