© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24097
    Prev
    Next
    INDEX
    Explanations

    phrases related to incorporation or reflection, especially in the context of systems or plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating incorporation or integration of ideas and concepts

    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
    hov
    -0.80
    ector
    -0.67
    ichi
    -0.64
    cert
    -0.63
    byter
    -0.63
    uku
    -0.62
    iscopal
    -0.62
    oried
    -0.61
    trak
    -0.60
    orius
    -0.60
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    0.72
     peoples
    0.68
     plain
    0.68
     somew
    0.66
     academia
    0.66
     society
    0.64
     workplaces
    0.64
     everyday
    0.62
     our
    0.61
     existing
    0.60
    Activations Density 0.372%

    No Known Activations