© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 11523
    Prev
    Next
    INDEX
    Explanations

    statistical likelihoods or probabilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate statistical likelihoods or probabilities of events occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zeb
    -0.80
    inelli
    -0.69
    ylan
    -0.66
    andan
    -0.65
    adel
    -0.65
    kind
    -0.64
    bane
    -0.64
    athom
    -0.64
    dust
    -0.64
    \\\\\\\\\\\\\\\\
    -0.63
    POSITIVE LOGITS
     prone
    0.80
     respondents
    0.72
     likely
    0.71
     to
    0.70
    âĢł
    0.69
     prey
    0.69
     than
    0.69
     infer
    0.67
     inclined
    0.67
     respondent
    0.65
    Activations Density 0.032%

    No Known Activations