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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20185
    Prev
    Next
    INDEX
    Explanations

    contact information for reporting crimes to Crime Stoppers organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to crime-related tips and reporting mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARB
    -0.71
    ME
    -0.67
    description
    -0.66
    rum
    -0.62
     Cath
    -0.62
     CAM
    -0.62
    sheet
    -0.62
    ARY
    -0.61
    MX
    -0.61
     CPS
    -0.61
    POSITIVE LOGITS
    oppers
    1.67
    terday
    0.96
    ĸļ
    0.87
    chedel
    0.82
    avascript
    0.80
     Klux
    0.79
    osate
    0.78
    culosis
    0.78
     billboards
    0.77
    kefeller
    0.77
    Activations Density 0.006%

    No Known Activations