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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29071
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    392
    +0.14
    0.7%
    287
    +0.12
    0.7%
    145
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.06
    156
    +0.12
    0.03
    271
    +0.12
    0.03
    Negative Logits
    utes
    -1.49
    ronic
    -1.47
    ults
    -1.45
    ats
    -1.44
     specs
    -1.34
    Rewrite
    -1.33
    ends
    -1.32
    NOTES
    -1.32
    inities
    -1.31
    Else
    -1.31
    POSITIVE LOGITS
    ĻĤ
    2.67
    ĥ½
    2.47
    ¿
    2.45
    °
    2.34
    ±
    2.31
    ´
    2.26
    ľĵ
    2.22
    ¥
    2.13
    ŀ
    2.06
    ³
    2.05
    Activations Density 0.009%

    No Known Activations