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. 2-RES-JB
    6. 8854
    Prev
    Next
    INDEX
    Explanations

    names of celebrities, particularly Alec Baldwin and Conor McGregor

    oai_token-act-pair · gpt-3.5-turbo

    names of prominent individuals mentioned in the context of entertainment and media

    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
    ening
    -0.77
    trap
    -0.71
    bang
    -0.66
    pring
    -0.66
    lets
    -0.64
    liga
    -0.64
    grades
    -0.64
    yg
    -0.64
    ened
    -0.63
    children
    -0.63
    POSITIVE LOGITS
     Conan
    0.99
    ovic
    0.96
    inition
    0.79
     Cumm
    0.78
    DIT
    0.77
    ventions
    0.77
     Guinness
    0.77
    thia
    0.76
     Fallon
    0.74
     Weir
    0.72
    Activations Density 0.015%

    No Known Activations