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. 8-RES-JB
    6. 16192
    Prev
    Next
    INDEX
    Explanations

    web links or commands typically found in an online discussion or forum setting

    oai_token-act-pair · gpt-3.5-turbo

    specific formatting symbols and characters often associated with coding or web links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     incorpor
    -0.69
     psychiat
    -0.68
     phosphorus
    -0.56
    geries
    -0.55
     asphalt
    -0.52
     heroin
    -0.52
    iewicz
    -0.51
     hook
    -0.51
     mount
    -0.51
     cones
    -0.51
    POSITIVE LOGITS
    Twitter
    0.78
    Spoiler
    0.72
    Balt
    0.70
    cffffcc
    0.68
    CNN
    0.68
    âĶĢâĶĢâĶĢâĶĢ
    0.68
    iced
    0.65
    YouTube
    0.65
    www
    0.65
    redd
    0.65
    Activations Density 0.394%

    No Known Activations