© 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. 4-RES-JB
    11. 3945
    Prev
    Next
    INDEX
    Explanations

    mentions of the words "Dra" and "Kra" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific brand or product, particularly beers and their variations

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

    No Comments

    Negative Logits
     GOODMAN
    -0.75
    LESS
    -0.71
    ARC
    -0.68
    ORE
    -0.68
     DOE
    -0.67
     Miranda
    -0.67
     Corpus
    -0.65
     Puerto
    -0.65
     FISA
    -0.63
     Catalonia
    -0.62
    POSITIVE LOGITS
    ught
    1.32
    fters
    1.24
    ven
    1.20
    enei
    1.12
    plin
    1.06
    fter
    1.06
    uth
    1.03
    ugh
    1.02
    bling
    1.01
    plets
    0.99
    Activations Density 0.010%

    No Known Activations