Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26841
    Prev
    Next
    INDEX
    Explanations

    intensifiers or modifiers that emphasize sentiment

    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
    23
    +0.14
    0.8%
    125
    +0.14
    0.8%
    375
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.14
    0.06
    394
    +0.14
    0.07
    125
    +0.14
    0.05
    Negative Logits
     thereof
    -1.74
     thereto
    -1.70
     therefrom
    -1.70
    ÃŃs
    -1.65
    iers
    -1.59
    ungen
    -1.50
    ļ
    -1.48
    ledge
    -1.47
    ÃŃas
    -1.46
     therein
    -1.44
    POSITIVE LOGITS
    thing
    1.76
     luck
    1.74
    minded
    1.59
    expensive
    1.59
    abouts
    1.54
    bred
    1.51
    ble
    1.48
    ston
    1.44
    much
    1.42
     disagree
    1.39
    Activations Density 0.091%

    No Known Activations