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. 15426
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to significant elements or themes in a narrative context

    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
    culosis
    -0.90
     Regarding
    -0.87
     Including
    -0.85
     Therefore
    -0.84
     [+
    -0.80
    ajor
    -0.80
    DT
    -0.80
    ICE
    -0.79
    termination
    -0.78
    TN
    -0.78
    POSITIVE LOGITS
     dazzling
    1.33
     towering
    1.31
     enigmatic
    1.27
     uncanny
    1.26
     sleek
    1.26
     eerie
    1.26
     bleak
    1.22
     shadowy
    1.22
     sprawling
    1.22
     stark
    1.20
    Activations Density 0.519%

    No Known Activations