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. 4551
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing feedback or commentary on a task

    oai_token-act-pair · gpt-3.5-turbo
    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
     Kissinger
    -0.79
     Rhodes
    -0.75
    outhern
    -0.74
    abama
    -0.74
     Negro
    -0.72
    Eastern
    -0.71
     Ventura
    -0.70
     southern
    -0.69
     Okin
    -0.69
     Bundy
    -0.68
    POSITIVE LOGITS
    Apps
    1.26
    ðŁij
    1.18
     iOS
    1.16
     iCloud
    1.13
    iOS
    1.12
     usability
    1.11
     apps
    1.11
     Dropbox
    1.10
     UX
    1.10
    ðŁĺ
    1.10
    Activations Density 0.843%

    No Known Activations