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. 18377
    Prev
    Next
    INDEX
    Explanations

    information related to accomplishments or activities of individuals

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate actions taken by individuals during a time frame

    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
    pmwiki
    -0.69
    SPONSORED
    -0.68
    etc
    -0.67
    Characters
    -0.66
    Anyway
    -0.62
    .–
    -0.61
    Attach
    -0.60
    .[
    -0.60
    intend
    -0.60
    aspx
    -0.59
    POSITIVE LOGITS
     his
    1.19
     himself
    0.99
     274
    0.80
     149
    0.79
     Wednesday
    0.79
     129
    0.79
     Tuesday
    0.79
     34
    0.78
     332
    0.78
     27
    0.78
    Activations Density 0.391%

    No Known Activations