© 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. 1-RES-SM
    11. 26188
    Prev
    Next
    INDEX
    Explanations

    occurrences of web addresses or URLs

    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
    336
    +0.11
    0.6%
    204
    +0.11
    0.6%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.11
    0.04
    204
    +0.11
    0.05
    335
    +0.10
    0.04
    Negative Logits
     due
    -1.69
     disturbance
    -1.67
     fle
    -1.60
     toler
    -1.55
    InstanceState
    -1.48
     disturbances
    -1.48
     =>
    -1.46
     recess
    -1.45
     penalties
    -1.44
     recovery
    -1.44
    POSITIVE LOGITS
    journals
    2.14
    cdn
    1.91
    php
    1.70
    room
    1.62
    club
    1.62
     website
    1.57
    story
    1.56
    ustration
    1.56
    iaz
    1.56
    pg
    1.54
    Activations Density 0.306%

    No Known Activations