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. 3005
    Prev
    Next
    INDEX
    Explanations

    phrases related to the degree of understanding or knowledge about a subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the quality of research and its recognition in academic literature

    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
     Fuck
    -0.67
     Shutdown
    -0.65
     idiots
    -0.65
     boarding
    -0.65
     Streaming
    -0.65
     Bulk
    -0.63
    amily
    -0.62
    uci
    -0.62
     bonuses
    -0.62
     Pork
    -0.61
    POSITIVE LOGITS
    documented
    1.41
     understood
    1.40
     documented
    1.27
    known
    1.24
     explored
    1.23
     debated
    1.20
     studied
    1.19
     recognised
    1.18
    established
    1.17
    defined
    1.15
    Activations Density 0.185%

    No Known Activations