© 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. 29685
    Prev
    Next
    INDEX
    Explanations

    patterns related to file handling and validation statuses in a database context

    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
    78
    +0.12
    0.7%
    186
    +0.10
    0.6%
    320
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.12
    0.06
    136
    +0.10
    -0.07
    85
    +0.10
    0.02
    Negative Logits
    §
    -2.79
    ¯
    -2.64
    Ħ
    -2.62
    ģ
    -2.60
    ·
    -2.49
    ¢
    -2.48
    ©
    -2.41
    ¬
    -2.38
    £
    -2.32
    Ń
    -2.28
    POSITIVE LOGITS
    ientos
    1.51
     Reporting
    1.42
     Haiti
    1.41
    opy
    1.40
     neut
    1.39
     thrive
    1.38
    catch
    1.38
    hurst
    1.33
     rescue
    1.32
    osp
    1.29
    Activations Density 3.336%

    No Known Activations