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. 29164
    Prev
    Next
    INDEX
    Explanations

    references to pre-study or preliminary stages in research contexts

    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
    46
    +0.13
    0.7%
    218
    +0.12
    0.7%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.13
    0.02
    46
    +0.12
    0.02
    374
    +0.12
    0.02
    Negative Logits
    Ĵ
    -2.70
    ľĵ
    -2.63
    Į
    -2.45
    ĻĤ
    -2.43
    £
    -2.39
    °
    -2.34
    ĸ´
    -2.34
    İ
    -2.34
    Ķ
    -2.27
    ĥ
    -2.27
    POSITIVE LOGITS
    fecture
    1.96
    historic
    1.70
    ppers
    1.57
    zzo
    1.54
    ceeding
    1.53
     awarded
    1.52
    clamation
    1.51
    -
    1.51
    iser
    1.48
     shipment
    1.45
    Activations Density 0.052%

    No Known Activations