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. 8225
    Prev
    Next
    INDEX
    Explanations

    references to limitations or restrictions on various actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to limitations and restrictions

    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
    lehem
    -0.71
    iron
    -0.66
    çīĪ
    -0.65
    fortune
    -0.65
    ished
    -0.65
    idon
    -0.63
    USS
    -0.63
    fort
    -0.62
    itch
    -0.61
     NEWS
    -0.59
    POSITIVE LOGITS
     allowable
    1.46
     permissible
    1.31
     permitted
    1.11
     allowed
    1.11
     freedoms
    1.04
     exceptions
    1.04
     scope
    1.00
     exemptions
    0.95
     possibilities
    0.93
     types
    0.91
    Activations Density 0.263%

    No Known Activations