© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21221
    Prev
    Next
    INDEX
    Explanations

    instructions or directives related to coordinating tasks and managing projects

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to examination and evaluation processes

    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
    death
    -0.83
    apo
    -0.79
    ãĥ´ãĤ¡
    -0.74
    lus
    -0.74
    toggle
    -0.74
    anus
    -0.74
    Death
    -0.73
     revenge
    -0.72
     booze
    -0.72
    ãĥ¢
    -0.71
    POSITIVE LOGITS
     collabor
    1.02
     knowledgeable
    1.00
     informative
    0.99
     collaborative
    0.98
     insightful
    0.98
     learners
    0.94
     educational
    0.93
     mentors
    0.92
     referrals
    0.92
     Cosponsors
    0.92
    Activations Density 1.206%

    No Known Activations