© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 4083
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "includes."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "includes."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whim
    -0.61
     desperation
    -0.59
     meth
    -0.58
     helpless
    -0.57
     desperate
    -0.57
     lap
    -0.56
     powerless
    -0.55
     cyn
    -0.54
     hun
    -0.54
     ripe
    -0.52
    POSITIVE LOGITS
     includes
    3.44
    includes
    2.49
     Includes
    2.46
     include
    2.33
     excludes
    2.27
     encompasses
    2.21
     comprises
    2.13
     included
    2.10
    Includes
    2.01
     incorporates
    1.99
    Activations Density 0.020%

    No Known Activations