Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22842
    Prev
    Next
    INDEX
    Explanations

    sights and landmarks in various locations

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    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
     warr
    -0.96
     consistency
    -0.86
     questioning
    -0.86
     mathemat
    -0.86
     inconsistency
    -0.86
     snowball
    -0.84
     hamstring
    -0.83
     aggress
    -0.83
     mascul
    -0.81
     surrogate
    -0.81
    POSITIVE LOGITS
     Located
    2.09
    Located
    1.97
     Built
    1.71
    Built
    1.58
     Visitors
    1.57
     Residents
    1.55
    Constructed
    1.45
     Its
    1.42
     Designed
    1.36
    Construction
    1.36
    Activations Density 0.351%

    No Known Activations