© 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. 4946
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations or judgments, with an emphasis on expressing a strong opinion

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" as well as various forms of expressions conveying positivity or significance

    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
    units
    -0.81
    notes
    -0.80
    ENTS
    -0.78
    Versions
    -0.77
    effects
    -0.70
    aways
    -0.69
    mill
    -0.67
    DragonMagazine
    -0.66
    resp
    -0.66
    otte
    -0.66
    POSITIVE LOGITS
     shame
    1.44
     pity
    1.37
     testament
    1.23
     coincidence
    1.21
     misconception
    1.12
     matter
    1.10
     reminder
    1.09
     miracle
    1.07
     cliché
    1.05
     fascinating
    1.04
    Activations Density 0.135%

    No Known Activations