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. 2455
    Prev
    Next
    INDEX
    Explanations

    names of scholars, writers, and public figures

    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
     srfAttach
    -0.75
    window
    -0.74
    twitch
    -0.73
    Plex
    -0.73
     actionGroup
    -0.72
    venge
    -0.72
    Emergency
    -0.69
    FTWARE
    -0.67
    crew
    -0.65
     Tradable
    -0.65
    POSITIVE LOGITS
     argues
    1.59
     writes
    1.40
     cites
    1.39
     summarizes
    1.38
     discusses
    1.35
     concludes
    1.34
     contends
    1.33
     argued
    1.31
     observes
    1.30
     asserts
    1.30
    Activations Density 0.367%

    No Known Activations