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. 4559
    Prev
    Next
    INDEX
    Explanations

    language indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo
    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
    MpServer
    -0.87
    ourning
    -0.86
    oother
    -0.76
     Presents
    -0.75
    papers
    -0.74
     "$:/
    -0.72
    organized
    -0.72
    doi
    -0.70
    knit
    -0.70
     Skydragon
    -0.70
    POSITIVE LOGITS
     remark
    1.89
     comment
    1.60
     statement
    1.57
     assertion
    1.51
     accusation
    1.46
     remarks
    1.41
     allegation
    1.37
     quote
    1.37
     characterization
    1.33
     quotation
    1.29
    Activations Density 0.404%

    No Known Activations