© 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. 2796
    Prev
    Next
    INDEX
    Explanations

    negations and phrases indicating the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    negative or contrasting statements

    oai_token-act-pair · gpt-3.5-turbo
    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
    ugh
    -0.74
    inks
    -0.71
    kamp
    -0.70
    çīĪ
    -0.69
    ows
    -0.67
    yes
    -0.67
    onyms
    -0.66
    need
    -0.66
    USH
    -0.65
    çļ
    -0.64
    POSITIVE LOGITS
     necessarily
    1.22
    icable
    1.15
     indicative
    1.12
     conducive
    1.03
     uncommon
    1.02
     unreasonable
    1.02
     conclusive
    1.00
     terribly
    0.99
     exhaustive
    0.99
    withstanding
    0.97
    Activations Density 0.174%

    No Known Activations