© 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. 18440
    Prev
    Next
    INDEX
    Explanations

    references to the shape of objects or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to shapes and their descriptions

    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
    onte
    -0.75
     Mub
    -0.72
    iance
    -0.71
    govtrack
    -0.71
     Edited
    -0.67
    aires
    -0.64
    unts
    -0.63
    endment
    -0.62
    ources
    -0.60
     Skies
    -0.60
    POSITIVE LOGITS
     shif
    0.94
     shape
    0.86
    shape
    0.83
     shapes
    0.81
    ly
    0.78
    Shape
    0.78
    nel
    0.77
    cut
    0.77
    forms
    0.76
    sheet
    0.75
    Activations Density 0.037%

    No Known Activations