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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 15704
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to research methods and data analysis

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittee
    -0.82
    redit
    -0.80
    ammy
    -0.77
    uphem
    -0.73
     rightfully
    -0.72
    starter
    -0.72
     counselors
    -0.72
    utch
    -0.71
    udeb
    -0.70
    rists
    -0.68
    POSITIVE LOGITS
     dynamics
    1.28
     interactions
    1.20
     traject
    1.19
     patterns
    1.19
     variability
    1.15
     microbial
    1.15
     evolution
    1.14
     molecular
    1.11
     rhythms
    1.10
     behaviour
    1.10
    Activations Density 0.346%

    No Known Activations