© 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. 4379
    Prev
    Next
    INDEX
    Explanations

    words related to power, control, or authority

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "ultimate" or "ultimacy."

    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
    manship
    -0.78
    STON
    -0.71
    BY
    -0.70
    TERN
    -0.66
    forth
    -0.65
    LOC
    -0.64
    creen
    -0.63
    hold
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.62
    avers
    -0.61
    POSITIVE LOGITS
    imately
    1.17
    raviolet
    1.14
    iple
    1.10
    urally
    1.02
    imates
    1.02
    ieth
    1.01
    ures
    1.00
    icultural
    0.97
    iful
    0.92
    ipl
    0.90
    Activations Density 0.022%

    No Known Activations