© 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. 8-RES-JB
    11. 3057
    Prev
    Next
    INDEX
    Explanations

    restrictions or prohibitions related to online gaming

    oai_token-act-pair · gpt-3.5-turbo

    technical jargon related to regulations or restrictions involving online activities

    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
     Turns
    -0.64
    riks
    -0.63
    lier
    -0.61
    zn
    -0.61
    veland
    -0.61
     Wander
    -0.61
    nell
    -0.60
    zzy
    -0.60
    Enlarge
    -0.60
    ideshow
    -0.59
    POSITIVE LOGITS
     respectively
    1.22
     irrespective
    1.16
     including
    1.12
     INCLUD
    1.11
     hereafter
    1.09
     pursuant
    1.09
     regardless
    1.06
     excluding
    1.05
     namely
    1.04
     Including
    1.02
    Activations Density 0.460%

    No Known Activations