© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28629
    Prev
    Next
    INDEX
    Explanations

    discussions related to construction and home maintenance

    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
    47
    +0.20
    1.2%
    419
    +0.18
    1.1%
    153
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.20
    0.17
    153
    +0.18
    0.07
    47
    +0.13
    0.19
    Negative Logits
    ĻĤ
    -2.31
    Ī
    -1.55
    ¬
    -1.51
    §
    -1.47
     franch
    -1.45
     author
    -1.42
    ĩ
    -1.41
    ¿½
    -1.40
    ı
    -1.40
    :*
    -1.40
    POSITIVE LOGITS
    bur
    1.77
     debris
    1.59
     pores
    1.53
    vas
    1.49
    óg
    1.47
    ulfide
    1.46
    iscus
    1.45
    destroy
    1.42
    oxin
    1.41
    opus
    1.40
    Activations Density 7.044%

    No Known Activations