© 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. 28033
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or criticism

    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
    203
    +0.14
    0.8%
    49
    +0.12
    0.7%
    313
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.03
    313
    +0.12
    0.02
    249
    +0.10
    0.02
    Negative Logits
    -"
    -1.59
    igt
    -1.47
    inux
    -1.45
    igos
    -1.44
    ilon
    -1.42
    ILITY
    -1.34
    ictionaries
    -1.33
    --"
    -1.33
    ynthesis
    -1.33
    illas
    -1.32
    POSITIVE LOGITS
     consideration
    1.63
    ]:
    1.59
    hearted
    1.51
    aways
    1.48
    VEN
    1.46
    cases
    1.42
    west
    1.40
    year
    1.36
    weather
    1.35
    union
    1.33
    Activations Density 0.128%

    No Known Activations