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. 7912
    Prev
    Next
    INDEX
    Explanations

    names and initials of individuals

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the letter 'C' in various contexts

    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
     MSG
    -0.67
     props
    -0.61
     bottleneck
    -0.61
     proof
    -0.61
     disadvantages
    -0.60
     promot
    -0.59
     productivity
    -0.58
     lur
    -0.58
     GOODMAN
    -0.58
     upward
    -0.57
    POSITIVE LOGITS
    ramer
    1.40
    avanaugh
    1.39
    rouch
    1.34
    lements
    1.32
    ohan
    1.17
    oker
    1.17
    resp
    1.17
    avan
    1.17
    isner
    1.16
    oving
    1.15
    Activations Density 0.026%

    No Known Activations