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. 10-RES-JB
    6. 21248
    Prev
    Next
    INDEX
    Explanations

    mentions of people's professions or titles in a formal context

    oai_token-act-pair · gpt-3.5-turbo

    articles that precede titles or roles in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iosity
    -0.72
    ombies
    -0.72
    eye
    -0.71
    Untitled
    -0.71
     asses
    -0.70
    boats
    -0.69
    EXP
    -0.69
    Episode
    -0.69
    Alien
    -0.67
    ittens
    -0.65
    POSITIVE LOGITS
     spokesman
    1.37
     spokeswoman
    1.26
     spokesperson
    1.25
     professor
    1.23
     lecturer
    1.20
     lawyer
    1.19
     longtime
    1.17
     consultant
    1.14
     researcher
    1.14
     former
    1.14
    Activations Density 0.076%

    No Known Activations