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. 26848
    Prev
    Next
    INDEX
    Explanations

    words related to detailed descriptions or factors affecting a subject

    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
    156
    +0.23
    1.3%
    111
    +0.16
    0.9%
    11
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.23
    0.21
    156
    +0.16
    0.10
    271
    +0.11
    0.09
    Negative Logits
    Ī
    -1.39
    00000000000000000000000000000000
    -1.38
    ¶
    -1.38
    instein
    -1.36
    isenberg
    -1.36
    ī
    -1.33
     ![](
    -1.32
    °
    -1.32
    hler
    -1.31
    `:
    -1.29
    POSITIVE LOGITS
    iary
    1.64
    endra
    1.56
    emen
    1.55
    ental
    1.54
    orter
    1.47
    ned
    1.47
     medic
    1.47
    ingly
    1.45
    lessly
    1.44
    anny
    1.43
    Activations Density 0.271%

    No Known Activations