© 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. 28794
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references

    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
    156
    +0.20
    1.1%
    368
    +0.13
    0.7%
    395
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.20
    0.04
    237
    +0.13
    0.12
    245
    +0.13
    0.11
    Negative Logits
    cean
    -1.62
    ļ
    -1.56
    etic
    -1.55
     matter
    -1.51
    sto
    -1.51
    rite
    -1.50
    ·
    -1.50
    hard
    -1.45
     son
    -1.44
    enter
    -1.43
    POSITIVE LOGITS
    Docket
    1.46
     folders
    1.45
    npmjs
    1.37
     directories
    1.36
    abine
    1.32
     pretext
    1.31
     forums
    1.30
    >).
    1.28
    reon
    1.28
    )->
    1.28
    Activations Density 3.759%

    No Known Activations