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. 29559
    Prev
    Next
    INDEX
    Explanations

    references to hemoglobin and related terms

    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
    156
    +0.15
    0.8%
    446
    +0.14
    0.8%
    347
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.15
    0.02
    18
    +0.14
    0.01
    347
    +0.10
    0.01
    Negative Logits
    ftware
    -1.90
    hip
    -1.74
    googleapis
    -1.56
    ffect
    -1.43
     hereby
    -1.43
     behalf
    -1.42
    hips
    -1.41
    hin
    -1.40
     hire
    -1.40
    IGNED
    -1.40
    POSITIVE LOGITS
    Ľ
    2.24
    ħ
    2.21
    ī
    2.04
    ĻĤ
    1.96
    odynamics
    1.94
    odynamic
    1.89
    ¹
    1.89
    İ
    1.89
    Ħ
    1.84
    Īĺ
    1.79
    Activations Density 0.070%

    No Known Activations