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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12206
    Prev
    Next
    INDEX
    Explanations

    references to the creation and copyright information in documents

    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
    21
    +0.13
    0.7%
    310
    +0.12
    0.7%
    128
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.13
    0.02
    79
    +0.12
    0.02
    74
    +0.12
    0.02
    Negative Logits
    usion
    -1.71
    ismatic
    -1.60
    lessly
    -1.50
    iNdEx
    -1.49
    distance
    -1.46
    carrier
    -1.44
    ITY
    -1.44
    hydrogen
    -1.43
    oltzmann
    -1.41
    str
    -1.41
    POSITIVE LOGITS
    ŀ
    1.75
     tomorrow
    1.65
     todd
    1.54
     grandson
    1.51
     birthday
    1.51
    thood
    1.46
    °
    1.45
    ĨĴ
    1.44
    umab
    1.42
    º
    1.42
    Activations Density 0.183%

    No Known Activations