© 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. 7-RES-JB
    11. 1480
    Prev
    Next
    INDEX
    Explanations

    medical terms or phrases related to health conditions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "inf," indicating a focus on words related to information or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.81
    OPLE
    -0.75
    姫
    -0.73
    hyde
    -0.71
    UAL
    -0.69
    BY
    -0.67
    Downloadha
    -0.67
     Blitz
    -0.66
    DragonMagazine
    -0.65
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    POSITIVE LOGITS
    usions
    1.20
    requent
    1.19
    requently
    1.18
    erno
    1.15
    ractions
    1.13
    ighting
    1.11
    raction
    1.09
    idelity
    1.09
    ortunately
    1.08
    estation
    1.08
    Activations Density 0.013%

    No Known Activations