© 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. 3-RES-JB
    11. 14726
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and programming terminology

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to specific topics and detailed classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.59
    KEY
    -0.54
     Kills
    -0.49
    pak
    -0.48
    ONEY
    -0.47
    olitics
    -0.47
     Jur
    -0.47
    ucha
    -0.45
     Reborn
    -0.45
     Auth
    -0.45
    POSITIVE LOGITS
    tenance
    0.84
    osterone
    0.69
    ãĤ´ãĥ³
    0.66
    ruction
    0.66
    terday
    0.63
    riors
    0.59
    iste
    0.58
    ãĥ³ãĤ¸
    0.58
    perature
    0.55
    vised
    0.54
    Activations Density 0.594%

    No Known Activations