© 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. 17222
    Prev
    Next
    INDEX
    Explanations

    words related to belts and belt buckles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Belt" and its variations in a specific context

    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
    ité
    -0.65
     Brist
    -0.65
    imates
    -0.64
     clocks
    -0.62
    itives
    -0.59
     HIP
    -0.58
     clock
    -0.58
     Sweeney
    -0.58
    mons
    -0.57
     Clapper
    -0.57
    POSITIVE LOGITS
     buckle
    1.08
    way
    1.02
    Line
    0.91
    fast
    0.88
    ran
    0.87
    wagon
    0.80
    ige
    0.79
    robe
    0.77
    rame
    0.77
    minster
    0.76
    Activations Density 0.071%

    No Known Activations