© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 7868
    Prev
    Next
    INDEX
    Explanations

    mentions of project-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to project funding and project proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    cers
    -0.72
     Koran
    -0.69
    rule
    -0.69
    lower
    -0.67
     marg
    -0.67
     Eddie
    -0.67
    lash
    -0.65
     soften
    -0.65
     hardness
    -0.65
     Boxing
    -0.65
    POSITIVE LOGITS
     projects
    1.59
    projects
    1.54
     Projects
    1.50
     project
    1.50
     undertaken
    1.42
     funded
    1.38
     endeavors
    1.38
     ambitious
    1.32
    project
    1.31
    Project
    1.30
    Activations Density 0.468%

    No Known Activations