© 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. 8-RES-JB
    11. 7068
    Prev
    Next
    INDEX
    Explanations

    terms related to serial occurrences or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to serial crimes, particularly those involving sexual offenses

    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
    luck
    -0.81
    wich
    -0.76
    aneers
    -0.76
    reath
    -0.74
    berman
    -0.73
    ynski
    -0.70
    olicy
    -0.69
    riel
    -0.69
     Syri
    -0.68
    uden
    -0.67
    POSITIVE LOGITS
    ized
    1.16
    isation
    1.06
    ization
    1.04
    ised
    1.02
    izable
    1.01
    izations
    0.97
    izing
    0.91
     killers
    0.91
    izers
    0.90
    izes
    0.88
    Activations Density 0.038%

    No Known Activations