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. 10-RES-JB
    6. 10862
    Prev
    Next
    INDEX
    Explanations

    references to legal or financial matters

    oai_token-act-pair · gpt-3.5-turbo

    references to regulatory actions or warnings related to financial practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ©
    -0.78
    romptu
    -0.76
     blond
    -0.73
    aciously
    -0.73
    »Ĵ
    -0.70
    ateful
    -0.70
    sylv
    -0.69
     afterward
    -0.68
     allegiance
    -0.68
     bloody
    -0.68
    POSITIVE LOGITS
    Companies
    1.29
     FTC
    1.23
     Companies
    1.23
     Consumer
    1.20
     VMware
    1.20
     ASIC
    1.18
     automakers
    1.17
     Consumers
    1.17
     Securities
    1.16
     Telecom
    1.15
    Activations Density 0.937%

    No Known Activations