© 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. 24588
    Prev
    Next
    INDEX
    Explanations

    instances of commas and other punctuation marks

    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
    23
    +0.17
    1.0%
    203
    +0.14
    0.8%
    391
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.17
    0.18
    467
    +0.14
    0.11
    136
    +0.11
    -0.01
    Negative Logits
    ĻĤ
    -5.64
    Ń
    -5.50
    «
    -5.49
    ¿
    -5.40
    ¿½
    -5.35
    ¼
    -5.28
    ĸ´
    -5.28
    ¾
    -5.25
    »¿
    -5.23
    Īĺ
    -5.19
    POSITIVE LOGITS
    signed
    1.48
    ]"
    1.45
    omitempty
    1.37
     huh
    1.35
    rapper
    1.35
    riton
    1.33
    =======================
    1.30
    #####
    1.30
     }\
    1.30
    ."_
    1.29
    Activations Density 1.483%

    No Known Activations