© 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. 10-RES-JB
    11. 24043
    Prev
    Next
    INDEX
    Explanations

    technical information or updates on software releases

    oai_token-act-pair · gpt-3.5-turbo

    references to specific data or news about games and media releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.81
    ictionary
    -0.81
    akespeare
    -0.79
     decriminal
    -0.77
    ocide
    -0.75
     constitutional
    -0.74
    CHAPTER
    -0.73
    âĢ¢âĢ¢
    -0.73
     sclerosis
    -0.73
     UNCLASSIFIED
    -0.72
    POSITIVE LOGITS
     teaser
    1.65
     leaked
    1.47
     teased
    1.33
     screenshots
    1.23
     preview
    1.22
     rumors
    1.20
     tease
    1.19
     teasing
    1.19
     previews
    1.18
     rumor
    1.15
    Activations Density 0.615%

    No Known Activations