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. 11-RES-JB
    6. 2915
    Prev
    Next
    INDEX
    Explanations

    information about professionals such as actors, comedians, writers, directors, producers, singers, songwriters, critics, authors, and columnists

    oai_token-act-pair · gpt-3.5-turbo

    names and titles of various professions and roles

    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
    ouses
    -0.92
    ements
    -0.86
    yles
    -0.81
    selves
    -0.80
    ares
    -0.80
    éĹĺ
    -0.79
    akedown
    -0.78
    ittens
    -0.77
    akings
    -0.77
    ittees
    -0.76
    POSITIVE LOGITS
     novelist
    1.65
     filmmaker
    1.60
     educator
    1.52
     entrepreneur
    1.51
     writer
    1.50
     poet
    1.49
     musician
    1.48
     journalist
    1.46
     philosopher
    1.45
     photographer
    1.45
    Activations Density 0.227%

    No Known Activations