© 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. 8-RES-JB
    11. 17117
    Prev
    Next
    INDEX
    Explanations

    numbers representing percentages

    oai_token-act-pair · gpt-3.5-turbo

    statistical data or numerical quantities related to percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folk
    -0.61
    Agent
    -0.61
    Plan
    -0.61
    Depth
    -0.60
    verages
    -0.59
    plan
    -0.58
    rade
    -0.58
    Fal
    -0.58
    rium
    -0.58
     RTX
    -0.57
    POSITIVE LOGITS
    %"
    1.25
    %
    1.13
     percent
    1.12
     000
    0.98
     thousand
    0.97
     million
    0.95
    %.
    0.95
    %:
    0.95
    %;
    0.93
     acres
    0.90
    Activations Density 0.126%

    No Known Activations