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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-SM
    6. 29168
    Prev
    Next
    INDEX
    Explanations

    important adjectives describing experiences or situations

    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
    326
    +0.16
    0.9%
    218
    +0.15
    0.9%
    198
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.10
    326
    +0.15
    0.07
    379
    +0.15
    0.10
    Negative Logits
    adesh
    -1.79
    appings
    -1.71
    endas
    -1.69
    ptions
    -1.64
    plitudes
    -1.63
    falls
    -1.59
    isma
    -1.58
    ments
    -1.53
     boundaries
    -1.50
    etine
    -1.49
    POSITIVE LOGITS
    Ĵ
    2.40
    ŀ
    2.28
    ļ
    2.13
    ©
    2.12
    Ĩ
    2.03
    FFIRMED
    1.99
    IJ
    1.97
    §
    1.96
    °
    1.96
    ¢
    1.96
    Activations Density 0.987%

    No Known Activations