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. 9-RES-JB
    6. 9494
    Prev
    Next
    INDEX
    Explanations

    questions about identity, responsibility, and authority

    oai_token-act-pair · gpt-3.5-turbo

    references to questioned identities and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Locations
    -0.74
    framework
    -0.74
    iation
    -0.68
    nothing
    -0.67
    ranging
    -0.66
    irth
    -0.66
    inery
    -0.66
    ossibility
    -0.65
    requ
    -0.65
    avascript
    -0.65
    POSITIVE LOGITS
     whom
    0.98
     responsible
    0.83
     footing
    0.80
     accountable
    0.79
     wiser
    0.75
    ?]
    0.75
    who
    0.75
     benef
    0.73
     cheated
    0.72
     cyn
    0.71
    Activations Density 0.119%

    No Known Activations