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. 684
    Prev
    Next
    INDEX
    Explanations

    technology-related terms and activities, such as smartphone applications, laptops, and photos on Twitter

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to tools, applications, and societal issues

    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
    )=
    -0.61
    )))
    -0.55
    ]=
    -0.55
    ))))
    -0.53
     Participant
    -0.53
    UTC
    -0.52
    ]).
    -0.50
     Prediction
    -0.50
    Topic
    -0.49
     belongs
    -0.49
    POSITIVE LOGITS
     or
    1.00
     themselves
    0.98
     lately
    0.86
     ranging
    0.83
     preferring
    0.81
     apiece
    0.79
     hoping
    0.78
     owing
    0.76
     fearing
    0.76
     amid
    0.75
    Activations Density 0.626%

    No Known Activations