Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7041
    Prev
    Next
    INDEX
    Explanations

    words related to specific professional roles or organizations

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to professions and roles in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAPTER
    -0.72
    FINE
    -0.70
    amina
    -0.66
     meas
    -0.63
     pleas
    -0.62
    ormonal
    -0.62
     corrid
    -0.61
     fortun
    -0.60
    haar
    -0.60
    abus
    -0.59
    POSITIVE LOGITS
    iasco
    0.72
     Crimes
    0.70
     Cyn
    0.69
     LLP
    0.68
    utra
    0.65
    plates
    0.64
     Ltd
    0.63
     Drops
    0.62
    plex
    0.62
     Square
    0.62
    Activations Density 0.605%

    No Known Activations