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. 29191
    Prev
    Next
    INDEX
    Explanations

    the preposition "in" in various 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
    95
    +0.12
    0.7%
    69
    +0.11
    0.7%
    159
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.02
    194
    +0.11
    0.01
    249
    +0.11
    0.01
    Negative Logits
     stained
    -1.56
    eter
    -1.50
    raits
    -1.48
    er
    -1.43
     fans
    -1.41
    _[
    -1.37
    waves
    -1.36
     reminds
    -1.35
    eur
    -1.34
    ouin
    -1.29
    POSITIVE LOGITS
    ĥ½
    1.89
    completion
    1.49
     fact
    1.49
    ousand
    1.44
     :=
    1.40
    vasive
    1.40
     compliance
    1.38
    applic
    1.37
    fileID
    1.34
    clusion
    1.33
    Activations Density 0.039%

    No Known Activations