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. 26711
    Prev
    Next
    INDEX
    Explanations

    references to specimens and their descriptions in scientific 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/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
    +0.26
    1.5%
    19
    +0.14
    0.8%
    361
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.26
    0.02
    344
    +0.14
    0.01
    19
    +0.13
    0.02
    Negative Logits
    §
    -4.89
    ĥ
    -4.39
    Ń
    -4.36
    ¥
    -4.29
    ĩ
    -4.10
    ®
    -4.08
    ķ
    -4.07
    ī
    -4.05
    ĭ
    -4.04
    į
    -4.02
    POSITIVE LOGITS
    ière
    1.93
    icro
    1.86
    othe
    1.72
    eria
    1.72
    arial
    1.68
     resembling
    1.68
    agraph
    1.65
     collection
    1.64
     sized
    1.58
    ICO
    1.56
    Activations Density 0.098%

    No Known Activations