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. 7-RES-JB
    6. 18607
    Prev
    Next
    INDEX
    Explanations

    pieces of text that describe visual scenes or situations

    oai_token-act-pair · gpt-3.5-turbo

    sentences with strong punctuation, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affili
    -0.76
    uly
    -0.75
     correct
    -0.75
    è¦ļéĨĴ
    -0.73
    omics
    -0.71
     fraud
    -0.70
     relevant
    -0.69
     appropriate
    -0.69
     consistency
    -0.69
     appoint
    -0.68
    POSITIVE LOGITS
     Suddenly
    1.23
     Occasionally
    1.18
     Moments
    1.14
     Dozens
    1.12
     Each
    1.07
     Across
    1.04
     Then
    1.04
     Slowly
    1.01
     Minutes
    1.01
     Sitting
    1.01
    Activations Density 0.275%

    No Known Activations