© 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. 10-RES-JB
    11. 6214
    Prev
    Next
    INDEX
    Explanations

    adjectives related to uncertainty and vagueness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to vagueness and lack of clarity

    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
    rators
    -0.83
    Drive
    -0.77
    Cross
    -0.77
    cross
    -0.74
    gression
    -0.73
    die
    -0.73
    din
    -0.72
    erver
    -0.70
    cedented
    -0.70
    edit
    -0.69
    POSITIVE LOGITS
     notions
    1.21
     notion
    1.13
     recollection
    1.11
     glimps
    1.02
     resemblance
    1.00
     beginnings
    0.98
     semblance
    0.96
     recol
    0.94
     existence
    0.91
     approximation
    0.90
    Activations Density 0.160%

    No Known Activations