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. 2-RES-SM
    6. 29444
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to equations

    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
    30
    +0.12
    0.7%
    478
    +0.12
    0.6%
    423
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    423
    +0.12
    0.02
    284
    +0.12
    0.02
    30
    +0.11
    0.01
    Negative Logits
     myself
    -1.62
    me
    -1.55
    apore
    -1.49
     mine
    -1.47
    ible
    -1.45
    quel
    -1.44
    cion
    -1.42
     yourself
    -1.41
    noreply
    -1.41
    ninger
    -1.40
    POSITIVE LOGITS
    ī
    5.62
    ¾
    5.22
    Ĩ
    5.21
    Ļ
    5.17
    µ
    5.14
    Ł
    5.10
    ®
    5.07
    İ
    4.92
    ¶
    4.89
    ħ
    4.85
    Activations Density 0.071%

    No Known Activations