© 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. 6-RES-JB
    11. 11977
    Prev
    Next
    INDEX
    Explanations

    names and terms related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    endings of sentences or paragraphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bound
    -0.65
    GN
    -0.64
    leg
    -0.61
    Bomb
    -0.60
    aqu
    -0.60
    ASC
    -0.59
    MX
    -0.57
    MP
    -0.57
    cash
    -0.56
    INC
    -0.56
    POSITIVE LOGITS
    姫
    0.90
    abwe
    0.83
    Ó
    0.77
    ãĥ¼ãĥĨ
    0.77
    uyomi
    0.77
    ãĤ¼ãĤ¦ãĤ¹
    0.76
    ¬¼
    0.74
    ulty
    0.73
    theless
    0.72
    ãĥĨãĤ£
    0.71
    Activations Density 0.149%

    No Known Activations