Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1151
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to mathematical concepts, such as "set", "Mandelbrot", and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mathematical concepts and structures

    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
    •EggList

    No Comments

    Negative Logits
     Julie
    -0.81
    hered
    -0.80
     Bauer
    -0.78
     disapp
    -0.77
    ogene
    -0.75
    ived
    -0.69
    NetMessage
    -0.69
    IFE
    -0.64
    auer
    -0.64
     adul
    -0.63
    POSITIVE LOGITS
    t
    1.36
    tty
    1.21
    tz
    1.21
    T
    1.19
    TD
    1.19
    ts
    1.18
    td
    1.17
    Ts
    1.13
    ta
    1.12
    TA
    1.12
    Activations Density 0.251%

    No Known Activations