© 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. 7120
    Prev
    Next
    INDEX
    Explanations

    people or entities being quoted for stating something

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    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
    aukee
    -0.74
    EMBER
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    andem
    -0.63
    arest
    -0.60
    backer
    -0.60
    tails
    -0.60
    ãĥ¡
    -0.59
    ãĥĺ
    -0.59
    ãĥīãĥ©
    -0.58
    POSITIVE LOGITS
     although
    0.81
     "[
    0.71
     contradicts
    0.71
     sounded
    0.69
     "#
    0.67
     they
    0.67
    cher
    0.67
     fateful
    0.63
     whilst
    0.60
     evening
    0.60
    Activations Density 0.252%

    No Known Activations