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. 14646
    Prev
    Next
    INDEX
    Explanations

    information related to historical and technical details

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

    instances of change and transformation within contexts

    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
    enei
    -0.70
    zers
    -0.65
     babe
    -0.62
    ovember
    -0.62
     deflation
    -0.61
     floats
    -0.60
    wrapper
    -0.59
     dri
    -0.59
     curv
    -0.59
    animate
    -0.59
    POSITIVE LOGITS
     founded
    0.89
     Instit
    0.86
     headquartered
    0.83
     Univers
    0.83
     Syndicate
    0.80
     Regions
    0.79
     Nationwide
    0.79
     specializing
    0.78
     Aware
    0.78
     Orbit
    0.78
    Activations Density 0.443%

    No Known Activations