© 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. 3236
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    specific patterns associated with social media handles or usernames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     resil
    -0.64
     corrections
    -0.62
     instruments
    -0.61
     peac
    -0.61
     instrument
    -0.60
     tense
    -0.59
     redevelop
    -0.59
     Palest
    -0.59
     Lauder
    -0.59
     contestant
    -0.59
    POSITIVE LOGITS
    df
    1.12
    cd
    1.10
    jj
    1.09
    Gh
    1.08
    jl
    1.06
    bc
    1.05
    zx
    1.05
    Ec
    1.04
    zn
    1.04
    bm
    1.00
    Activations Density 0.050%

    No Known Activations