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. 9-RES-JB
    6. 8503
    Prev
    Next
    INDEX
    Explanations

    people's occupations or roles

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing individuals and their professions or 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
     Watching
    -0.71
     Checking
    -0.71
    UME
    -0.68
     VIDEOS
    -0.67
    Kin
    -0.66
    CRIP
    -0.65
    OD
    -0.64
    HAM
    -0.64
    ARM
    -0.63
    PD
    -0.63
    POSITIVE LOGITS
     specializes
    1.30
     thri
    1.08
     wears
    1.05
     enjoys
    1.05
     seeks
    1.04
     loves
    1.01
     underwent
    1.01
     overcame
    1.01
     travels
    0.99
     strives
    0.98
    Activations Density 0.141%

    No Known Activations