© 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. 28798
    Prev
    Next
    INDEX
    Explanations

    references to abstract concepts or unspecified ideas

    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
    246
    +0.14
    0.8%
    365
    +0.12
    0.7%
    263
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.14
    0.04
    360
    +0.12
    0.03
    230
    +0.11
    0.02
    Negative Logits
    ¥
    -3.72
    Ļª
    -3.69
    §
    -3.21
    ¬
    -3.19
    µ
    -3.17
    Ń
    -3.13
    ·
    -3.12
    Ī
    -3.12
    ¿½
    -3.02
    ĺ
    -3.01
    POSITIVE LOGITS
     else
    2.83
     resembling
    2.01
     productive
    1.87
     ELSE
    1.81
     like
    1.73
    Else
    1.73
     positive
    1.60
     akin
    1.58
     acidic
    1.55
     constructive
    1.55
    Activations Density 0.100%

    No Known Activations