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. 9-RES-JB
    6. 18955
    Prev
    Next
    INDEX
    Explanations

    directives or instructions related to software installation and maintenance

    oai_token-act-pair · gpt-3.5-turbo

    key terms and phrases related to software installation and dependency management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cozy
    -0.66
    ghazi
    -0.65
    ileaks
    -0.65
     rive
    -0.64
    wow
    -0.64
    cellence
    -0.59
     hun
    -0.57
     Freak
    -0.57
     damn
    -0.57
     gut
    -0.57
    POSITIVE LOGITS
     exceptions
    1.02
     excludes
    0.97
    Example
    0.94
     Example
    0.91
     exception
    0.91
     defaults
    0.89
     expires
    0.88
     optionally
    0.88
     Alternatively
    0.87
     optional
    0.87
    Activations Density 0.626%

    No Known Activations