© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6501
    Prev
    Next
    INDEX
    Explanations

    quantitative descriptions or quantities, such as numbers, figures, dates, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    contexts involving large numbers or statistics that indicate significant impact or concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffen
    -0.79
     Neb
    -0.56
    fman
    -0.55
     iPads
    -0.54
     submar
    -0.53
     skiing
    -0.52
    agate
    -0.52
     lesbians
    -0.52
     Hulu
    -0.51
     FedEx
    -0.50
    POSITIVE LOGITS
    oire
    0.52
    weet
    0.50
    eteria
    0.50
    noxious
    0.50
    athon
    0.50
     millenn
    0.50
    dinand
    0.50
    ARCH
    0.49
     clot
    0.49
     Trace
    0.48
    Activations Density 1.336%

    No Known Activations