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. 11-RES-JB
    6. 8989
    Prev
    Next
    INDEX
    Explanations

    information related to official meetings and hearings

    oai_token-act-pair · gpt-3.5-turbo

    references to formal meetings or hearings related to governance or oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anty
    -0.75
    Äĩ
    -0.73
    avorite
    -0.69
    uably
    -0.67
     reckoned
    -0.66
     Rowling
    -0.65
    renheit
    -0.65
     propel
    -0.64
    jug
    -0.64
    isters
    -0.61
    POSITIVE LOGITS
     meeting
    1.68
     meetings
    1.64
     hearings
    1.56
     briefing
    1.52
     hearing
    1.49
     briefings
    1.37
     consultations
    1.30
     consultation
    1.29
     conference
    1.26
     session
    1.21
    Activations Density 0.300%

    No Known Activations