© 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. 4-RES-SM
    11. 8991
    Prev
    Next
    INDEX
    Explanations

    words starting with the letter 'f'

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    225
    +0.12
    0.7%
    279
    +0.12
    0.7%
    386
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.12
    0.02
    37
    +0.12
    0.01
    225
    +0.11
    0.04
    Negative Logits
    een
    -1.88
    e
    -1.84
    UAL
    -1.75
    lace
    -1.70
    eur
    -1.68
    eren
    -1.66
    eer
    -1.65
    tel
    -1.62
    lov
    -1.62
    edin
    -1.56
    POSITIVE LOGITS
    inally
    2.17
    uzzy
    2.15
    ighters
    2.06
    erguson
    2.04
    avorite
    2.03
    idelity
    2.03
    ortun
    2.01
    rench
    1.97
    olds
    1.97
    amous
    1.96
    Activations Density 0.095%

    No Known Activations