© 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. 10-RES-JB
    11. 11419
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to opinions, claims, and estimations

    oai_token-act-pair · gpt-3.5-turbo

    references to personal opinions and statements made by individuals

    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
     actionGroup
    -0.69
    ebus
    -0.67
    clone
    -0.65
    appropriate
    -0.65
    adelphia
    -0.62
    estial
    -0.58
    eful
    -0.58
    ulla
    -0.57
     Portable
    -0.57
    ļéĨĴ
    -0.57
    POSITIVE LOGITS
     reasoned
    1.26
     argues
    1.20
     contends
    1.17
     argued
    1.14
     says
    1.13
     contended
    1.06
     said
    1.04
     argue
    1.01
     say
    1.01
     contend
    0.99
    Activations Density 0.208%

    No Known Activations