Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14853
    Prev
    Next
    INDEX
    Explanations

    words related to climbing or heights

    oai_token-act-pair · gpt-3.5-turbo

    references to climbing and related activities

    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
    Ô
    -0.78
    fold
    -0.72
    REDACTED
    -0.70
    present
    -0.68
    Hispanic
    -0.65
    medium
    -0.63
    cloth
    -0.62
    backer
    -0.62
    iveness
    -0.62
    joy
    -0.61
    POSITIVE LOGITS
     clim
    1.33
     Clim
    0.95
     climbers
    0.94
    acter
    0.90
     unbeliev
    0.88
    ierrez
    0.82
    byss
    0.82
     corrid
    0.80
     srf
    0.80
     proble
    0.78
    Activations Density 0.008%

    No Known Activations