© 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. 9-RES-JB
    11. 1589
    Prev
    Next
    INDEX
    Explanations

    information related to legal cases or judicial processes

    oai_token-act-pair · gpt-3.5-turbo

    references to statistical analysis and measurements in a data context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     badass
    -0.87
     goddamn
    -0.86
     fucking
    -0.86
     whilst
    -0.84
     brilliantly
    -0.82
     tragically
    -0.81
     shameless
    -0.77
     extraord
    -0.77
     grotesque
    -0.75
     horrend
    -0.75
    POSITIVE LOGITS
     spokeswoman
    0.83
    Asked
    0.82
     testers
    0.74
     spokesman
    0.74
    Adds
    0.74
     aides
    0.73
     timetable
    0.71
    Newsletter
    0.71
    CBC
    0.70
     Asked
    0.69
    Activations Density 1.467%

    No Known Activations