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. 20104
    Prev
    Next
    INDEX
    Explanations

    website and social media elements like buttons, links or instructions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating association or accompaniment

    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
    bilt
    -0.81
     cheaply
    -0.56
     storefront
    -0.51
     botched
    -0.50
     Establishment
    -0.50
    strate
    -0.50
    sov
    -0.50
     shore
    -0.50
     Beverly
    -0.50
     attempts
    -0.49
    POSITIVE LOGITS
    draw
    1.30
    drawn
    1.12
    holding
    1.10
     regard
    0.97
     regards
    0.88
    stood
    0.86
    held
    0.83
     impunity
    0.79
     respect
    0.79
     caution
    0.73
    Activations Density 0.067%

    No Known Activations