© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 14508
    Prev
    Next
    INDEX
    Explanations

    verbs expressing likelihood or possibility

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating possibilities or uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.64
     cardinal
    -0.64
    jri
    -0.61
    ailability
    -0.61
    ivism
    -0.59
    IV
    -0.57
     adolesc
    -0.57
     realism
    -0.56
    forms
    -0.56
     Glob
    -0.56
    POSITIVE LOGITS
     wondering
    1.08
     noticed
    1.07
     notice
    1.01
     wonder
    1.00
     guessed
    0.96
     wondered
    0.93
    swer
    0.87
     noticing
    0.84
     wanna
    0.84
     hearing
    0.81
    Activations Density 0.123%

    No Known Activations