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. 6-RES-JB
    6. 18146
    Prev
    Next
    INDEX
    Explanations

    web URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web-related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.34
     disadvant
    -0.32
     challeng
    -0.29
     undermin
    -0.29
     awa
    -0.28
     rul
    -0.27
     incent
    -0.27
     embr
    -0.26
    '."
    -0.26
     distingu
    -0.25
    POSITIVE LOGITS
     âĢº
    0.24
    Screenshot
    0.20
     screenshots
    0.20
    atform
    0.20
    owned
    0.19
    reenshots
    0.18
    cigarettes
    0.18
     guiActive
    0.18
    icol
    0.18
    osures
    0.17
    Activations Density 7.010%

    No Known Activations