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. 10-RES-JB
    6. 19698
    Prev
    Next
    INDEX
    Explanations

    mentions of other individuals or groups apart from the main focus

    oai_token-act-pair · gpt-3.5-turbo

    references to additional or different individuals in various contexts

    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
    opoly
    -0.81
    omics
    -0.79
    Market
    -0.78
    uncture
    -0.78
     proverb
    -0.78
    ategory
    -0.76
    ħĭ
    -0.76
    illus
    -0.76
    Policy
    -0.75
    Rating
    -0.73
    POSITIVE LOGITS
     occupants
    1.38
     victims
    1.35
     passengers
    1.30
     participants
    1.21
     residents
    1.17
     inmates
    1.17
     defendants
    1.16
     members
    1.16
     witnesses
    1.16
     detainees
    1.15
    Activations Density 0.263%

    No Known Activations