© 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. 28640
    Prev
    Next
    INDEX
    Explanations

    terms related to camera and lens specifications

    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
    +0.14
    0.8%
    248
    +0.13
    0.7%
    19
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    0.02
    188
    +0.13
    0.01
    306
    +0.11
    0.02
    Negative Logits
     drinking
    -1.74
     polite
    -1.51
    usement
    -1.51
     definite
    -1.44
     viv
    -1.43
     respectful
    -1.43
    ©
    -1.40
     vegan
    -1.39
     viral
    -1.38
     bargaining
    -1.37
    POSITIVE LOGITS
    rade
    1.93
    iscus
    1.89
    imetry
    1.72
    istors
    1.68
    ue
    1.67
    pectives
    1.64
     diameters
    1.64
    ief
    1.63
     brighter
    1.61
     diameter
    1.58
    Activations Density 0.124%

    No Known Activations