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. 12-RES-JB
    6. 15111
    Prev
    Next
    INDEX
    Explanations

    technical information related to auditing and inspection processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to regulatory compliance and inspections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     misunder
    -0.58
     Plans
    -0.56
     Edited
    -0.56
    olk
    -0.56
     Released
    -0.55
    illary
    -0.53
     Contributions
    -0.53
    rote
    -0.53
    adiq
    -0.53
    stros
    -0.53
    POSITIVE LOGITS
     every
    1.63
     regularly
    1.57
     frequently
    1.57
     occasionally
    1.49
     weekly
    1.47
     periodically
    1.47
     annually
    1.44
     daily
    1.42
     yearly
    1.41
    every
    1.40
    Activations Density 1.280%

    No Known Activations