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. 2-RES-JB
    6. 10089
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Bolton

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly "Bolton" and "Bil."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pring
    -0.82
    ULT
    -0.78
    anto
    -0.72
    atro
    -0.70
    avez
    -0.69
    ADRA
    -0.67
    pta
    -0.67
    pai
    -0.65
    itialized
    -0.63
     Offline
    -0.63
    POSITIVE LOGITS
     Bolton
    0.99
    mingham
    0.94
     Wand
    0.83
    abad
    0.70
    luaj
    0.69
     Bil
    0.68
    bing
    0.68
    combe
    0.67
    aughs
    0.67
     Hamm
    0.65
    Activations Density 0.012%

    No Known Activations