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. 1-RES-JB
    6. 4157
    Prev
    Next
    INDEX
    Explanations

    keywords related to product roadmaps and planning

    oai_token-act-pair · gpt-3.5-turbo

    references to project roadmaps and related planning concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abilia
    -0.87
    imar
    -0.85
    ieri
    -0.81
    reth
    -0.79
    ãĤ¢ãĥ«
    -0.78
    vin
    -0.76
    ista
    -0.76
    anooga
    -0.72
    minster
    -0.71
    omics
    -0.71
    POSITIVE LOGITS
     roadmap
    0.98
     Perspective
    0.70
    gpu
    0.69
    ND
    0.68
    PsyNetMessage
    0.67
    Recommend
    0.67
    mentioned
    0.65
     Gilmore
    0.65
     solitary
    0.63
    catentry
    0.63
    Activations Density 0.029%

    No Known Activations