© 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. 18539
    Prev
    Next
    INDEX
    Explanations

    nouns related to specific events or professions

    oai_token-act-pair · gpt-3.5-turbo

    statements about personal experiences and emotions

    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
    Furthermore
    -0.80
    éŃĶ
    -0.79
    etheless
    -0.76
    Moreover
    -0.76
    currently
    -0.74
    Indeed
    -0.73
    Nevertheless
    -0.72
    士
    -0.72
    é¾įå
    -0.72
    DATA
    -0.72
    POSITIVE LOGITS
    ,'"
    1.02
     fuckin
    0.93
    ,"
    0.92
    ,''
    0.90
     happiest
    0.89
     love
    0.89
    "—
    0.88
     [
    0.86
     gonna
    0.83
     daddy
    0.82
    Activations Density 0.659%

    No Known Activations