Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20590
    Prev
    Next
    INDEX
    Explanations

    domain names and website links ending with ".com" or ".com/"

    oai_token-act-pair · gpt-3.5-turbo

    URLs and references to web content

    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
     carving
    -0.77
     Rabbit
    -0.75
     Pillar
    -0.71
     smelling
    -0.70
     framed
    -0.69
     trapping
    -0.69
     framing
    -0.69
     constit
    -0.68
     dividing
    -0.66
     slit
    -0.66
    POSITIVE LOGITS
    com
    1.77
    edu
    1.16
    org
    1.14
    co
    1.12
    tumblr
    1.11
    wordpress
    1.10
    COM
    1.07
    sites
    1.07
    biz
    1.03
    net
    1.02
    Activations Density 0.033%

    No Known Activations