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

    Neuronpedia

    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. 9-RES-JB
    11. 21558
    Prev
    Next
    INDEX
    Explanations

    phrases related to upgrades, updates, and actions of holding law enforcement accountable

    oai_token-act-pair · gpt-3.5-turbo

    tokens denoting rating or updates related to content or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aliens
    -0.65
    uate
    -0.62
    ¯¯¯¯
    -0.60
     bonded
    -0.59
     Canaveral
    -0.58
    VICE
    -0.57
     Munich
    -0.57
     Fidel
    -0.57
    ¯¯¯¯¯¯¯¯
    -0.57
    士
    -0.57
    POSITIVE LOGITS
    stairs
    1.37
    dates
    1.32
    grading
    1.31
    grades
    1.30
    dating
    1.28
    bringing
    1.25
    coming
    1.23
    graded
    1.19
    rights
    1.17
    votes
    1.13
    Activations Density 0.046%

    No Known Activations