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. 11-RES-JB
    6. 18482
    Prev
    Next
    INDEX
    Explanations

    general items or objects described in a list format

    oai_token-act-pair · gpt-3.5-turbo

    references to included items and plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     butcher
    -0.78
     cos
    -0.69
     god
    -0.69
     suicide
    -0.67
     brid
    -0.67
     deck
    -0.66
     stuffing
    -0.66
     chim
    -0.65
     sketch
    -0.65
     modelling
    -0.64
    POSITIVE LOGITS
    ":["
    1.47
    ":[
    1.41
    âĦ¢:
    1.21
    {"
    1.17
    ":"","
    1.16
     [|
    1.15
    .:
    1.14
    ="/
    1.13
    .):
    1.12
    ":"/
    1.11
    Activations Density 0.073%

    No Known Activations