© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7677
    Prev
    Next
    INDEX
    Explanations

    statements related to climbing activities

    oai_token-act-pair · gpt-3.5-turbo

    references to climbing or climbers, particularly in dramatic contexts

    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
     Gutenberg
    -0.68
     interest
    -0.66
    fold
    -0.66
     margins
    -0.65
    DEP
    -0.64
     Mighty
    -0.63
     inclusive
    -0.61
     Interest
    -0.60
     inherited
    -0.60
     Moose
    -0.59
    POSITIVE LOGITS
    ber
    1.55
    actic
    1.38
    atic
    1.38
    bers
    1.37
    acter
    1.37
    bing
    1.20
    bons
    1.12
    atically
    1.11
    bors
    1.10
    bour
    1.06
    Activations Density 0.053%

    No Known Activations