© 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. 2427
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional responses

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey surprise or reaction to unexpected events

    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
    brance
    -0.78
    etting
    -0.77
    ylan
    -0.69
    bender
    -0.68
    hang
    -0.68
    externalActionCode
    -0.68
    agin
    -0.66
    utical
    -0.65
    uph
    -0.65
    ulture
    -0.65
    POSITIVE LOGITS
     someone
    0.95
     somebody
    0.88
     announ
    0.81
     commenters
    0.78
     they
    0.77
     anyone
    0.70
     others
    0.70
     confronted
    0.68
    soever
    0.67
     announcements
    0.66
    Activations Density 0.188%

    No Known Activations