© 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. 11-RES-JB
    11. 3845
    Prev
    Next
    INDEX
    Explanations

    details related to mountain climbing activities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to climbing statistics and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    intendo
    -1.03
     Rooney
    -0.88
    Ware
    -0.84
    Howard
    -0.82
     Fried
    -0.82
    oice
    -0.82
    Nintendo
    -0.78
     EA
    -0.77
    etchup
    -0.76
    asley
    -0.76
    POSITIVE LOGITS
     climbers
    2.07
     Everest
    2.01
     climbing
    1.85
     Himal
    1.71
     Clim
    1.71
     climbs
    1.69
     bould
    1.69
     climb
    1.66
     Yosemite
    1.64
     clim
    1.62
    Activations Density 0.460%

    No Known Activations