Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5655
    Prev
    Next
    INDEX
    Explanations

    shapes such as rectangles, triangles, circles, and ellipses

    oai_token-act-pair · gpt-3.5-turbo

    geometric shapes and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Idle
    -0.80
    ãģĹ
    -0.68
    verb
    -0.68
    ufact
    -0.67
     Cosponsors
    -0.66
    ãģ¦
    -0.66
    tested
    -0.65
    agents
    -0.63
     honesty
    -0.63
    VO
    -0.63
    POSITIVE LOGITS
     shaped
    1.41
     shape
    1.20
    shaped
    1.16
     prism
    1.11
     triangular
    1.03
     shapes
    1.00
     latt
    0.98
     spacing
    0.93
     rectangular
    0.91
     wedge
    0.90
    Activations Density 0.076%

    No Known Activations