© 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. 2-RES-SM
    11. 12601
    Prev
    Next
    INDEX
    Explanations

    terms related to effectiveness and performance

    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
    +0.35
    2.1%
    111
    +0.23
    1.4%
    187
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.35
    0.08
    156
    +0.23
    0.08
    473
    +0.16
    0.07
    Negative Logits
    ´
    -1.75
    ²
    -1.74
    »¿
    -1.64
    ±
    -1.60
    ³
    -1.52
    ½
    -1.41
    athan
    -1.41
    ĥ½
    -1.39
    STITUTE
    -1.39
    Ļ
    -1.37
    POSITIVE LOGITS
    ivities
    2.63
    ives
    2.26
    iveness
    2.17
    resses
    2.02
    ive
    1.84
     against
    1.74
    uality
    1.70
    ively
    1.69
    ivity
    1.67
    uate
    1.65
    Activations Density 0.091%

    No Known Activations