© 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. 6-RES-JB
    11. 20289
    Prev
    Next
    INDEX
    Explanations

    words related to shapes or forms

    oai_token-act-pair · gpt-3.5-turbo

    references to different shapes and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onte
    -0.71
     Mub
    -0.71
    govtrack
    -0.67
     Edited
    -0.66
    iance
    -0.66
    acqu
    -0.66
    ondo
    -0.64
    endment
    -0.64
    GS
    -0.63
    artment
    -0.63
    POSITIVE LOGITS
    shape
    1.00
     shape
    0.92
     shif
    0.90
    cut
    0.83
     shapes
    0.83
    lier
    0.76
    sheet
    0.76
     Shape
    0.76
    Shape
    0.75
    file
    0.74
    Activations Density 0.028%

    No Known Activations