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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 6012
    Prev
    Next
    INDEX
    Explanations

    words related to investigations and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of investigative processes and specific investigative entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuck
    -0.76
     Cot
    -0.73
    opian
    -0.72
    onyms
    -0.71
    inian
    -0.68
    brate
    -0.68
    boys
    -0.68
     Gibbs
    -0.66
    brates
    -0.64
    bags
    -0.64
    POSITIVE LOGITS
    ãĥ¼ãĥ
    0.76
    nown
    0.74
    ~~~~~~~~~~~~~~~~
    0.73
    omal
    0.73
    ational
    0.72
    itional
    0.72
     inval
    0.71
    NetMessage
    0.71
    ead
    0.69
    ressed
    0.69
    Activations Density 0.024%

    No Known Activations