© 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. 2-RES-SM
    11. 27840
    Prev
    Next
    INDEX
    Explanations

    the word "Cam" in various contexts and related terms

    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
    410
    +0.18
    1.0%
    156
    +0.15
    0.9%
    74
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.18
    0.03
    177
    +0.15
    0.02
    77
    +0.12
    0.01
    Negative Logits
    ĥ½
    -1.97
    »¿
    -1.89
    ĻĤ
    -1.78
    İ
    -1.67
    £
    -1.58
    uppose
    -1.55
    cession
    -1.52
    ¿½
    -1.52
     interest
    -1.51
     slightest
    -1.50
    POSITIVE LOGITS
    acho
    2.09
    arias
    1.91
    ilo
    1.84
    unda
    1.83
    oufl
    1.81
    illo
    1.76
    elijk
    1.69
    andro
    1.64
    ila
    1.61
    imir
    1.55
    Activations Density 0.135%

    No Known Activations