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. 9-RES-JB
    6. 1155
    Prev
    Next
    INDEX
    Explanations

    locations or positions of objects on the exterior or interior

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of physical locations and surfaces of objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yssey
    -0.90
    istani
    -0.83
    issance
    -0.82
    edIn
    -0.75
    arak
    -0.73
    zynski
    -0.71
    MQ
    -0.70
    oleon
    -0.68
    ongo
    -0.65
    fortune
    -0.65
    POSITIVE LOGITS
     thereof
    1.12
    most
    1.11
     diameter
    1.03
     surfaces
    0.99
     surface
    0.98
     underside
    0.98
     circumference
    0.98
     edges
    0.98
     rim
    0.97
     of
    0.95
    Activations Density 0.146%

    No Known Activations