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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14378
    Prev
    Next
    INDEX
    Explanations

    requests for users to resubscribe with a valid email address

    oai_token-act-pair · gpt-3.5-turbo

    directives or prompts related to email input and validation

    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
    anka
    -0.67
     wound
    -0.59
     partic
    -0.59
    urat
    -0.58
    assisted
    -0.56
     incidentally
    -0.55
     adv
    -0.54
    accompan
    -0.54
     groom
    -0.54
     intern
    -0.53
    POSITIVE LOGITS
     {*
    0.68
    php
    0.66
     Invalid
    0.62
    rition
    0.61
    Sorry
    0.61
     externalToEVAOnly
    0.60
     DISTRICT
    0.58
    ãĤº
    0.58
     BELOW
    0.57
     Constitutional
    0.57
    Activations Density 0.019%

    No Known Activations