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. 7-RES-JB
    6. 9146
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating a location or distance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ongoing political issues and campaign strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muster
    -0.78
     aggro
    -0.76
     showc
    -0.75
     logistical
    -0.75
     scra
    -0.74
     captcha
    -0.73
    addon
    -0.73
     crest
    -0.73
     toget
    -0.73
    ritten
    -0.73
    POSITIVE LOGITS
     Them
    1.14
     Relationship
    1.12
     Prevention
    1.09
     Profession
    1.09
     Month
    1.08
     Ages
    1.07
     Debate
    1.06
     Homeless
    1.05
     Aging
    1.04
     Names
    1.04
    Activations Density 0.382%

    No Known Activations