© 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. 1-RES-JB
    11. 24187
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of discomfort or agitation, specifically focusing on the concept of nerves

    oai_token-act-pair · gpt-3.5-turbo

    references to nerves and their impact on experiences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    option
    -0.72
    template
    -0.69
    role
    -0.68
    rooms
    -0.67
    orthy
    -0.66
    rama
    -0.66
    reek
    -0.66
    vari
    -0.66
    fficiency
    -0.65
    allow
    -0.65
    POSITIVE LOGITS
     nerves
    1.67
     nerve
    1.06
     tiss
    0.97
     numb
    0.80
     nervous
    0.79
     prick
    0.78
     tremend
    0.78
    wcs
    0.77
    ussen
    0.74
     endings
    0.73
    Activations Density 0.005%

    No Known Activations