© 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. 25180
    Prev
    Next
    INDEX
    Explanations

    sentences that conclude with a period

    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
    297
    +0.16
    0.9%
    302
    +0.14
    0.8%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.16
    0.00
    23
    +0.14
    0.00
    420
    +0.13
    0.00
    Negative Logits
     dots
    -1.52
    WARE
    -1.48
     anywhere
    -1.47
    ?)
    -1.46
     minded
    -1.36
    ĻĤ
    -1.34
    aphr
    -1.32
    lament
    -1.32
     dot
    -1.32
     jar
    -1.30
    POSITIVE LOGITS
    olip
    1.78
    ering
    1.60
    roscopic
    1.56
    âĢĥ
    1.55
    com
    1.53
    ophagy
    1.53
    fulness
    1.47
    escence
    1.46
     Ky
    1.45
    otransferase
    1.44
    Activations Density 0.000%

    No Known Activations