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. 19767
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing support, help, or aid to individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and phrases that emphasize the needs of individuals

    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
     Leilan
    -0.69
     sidelines
    -0.67
    ysis
    -0.65
    anian
    -0.57
    Newsletter
    -0.57
     inver
    -0.57
     observ
    -0.56
     exceptions
    -0.56
    mart
    -0.56
    living
    -0.55
    POSITIVE LOGITS
     crave
    1.22
     deserve
    1.18
     need
    1.15
     desired
    1.13
     needed
    1.13
     NEED
    1.12
     sorely
    1.09
    need
    1.09
     desperately
    1.08
     desire
    1.08
    Activations Density 0.119%

    No Known Activations