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. 3-RES-JB
    6. 2258
    Prev
    Next
    INDEX
    Explanations

    people or sources who are familiar or have experience with certain topics or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with authority or expertise in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Girls
    -0.88
    Baby
    -0.79
    Frames
    -0.78
    Beaut
    -0.77
    Lind
    -0.73
    Pokemon
    -0.72
    Teen
    -0.72
    Girl
    -0.72
    issan
    -0.71
    issy
    -0.70
    POSITIVE LOGITS
     briefed
    1.09
     aide
    1.03
     aides
    1.00
     briefings
    0.99
     insider
    0.99
     staffer
    0.98
     memos
    0.98
     sworn
    0.95
     staffers
    0.93
     associates
    0.90
    Activations Density 0.325%

    No Known Activations