© 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. 11-RES-JB
    11. 14942
    Prev
    Next
    INDEX
    Explanations

    themes related to storytelling, blending elements of different genres or styles to create new narratives

    oai_token-act-pair · gpt-3.5-turbo

    combinations of humor and storytelling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Otherwise
    -0.61
    ©¶æ¥µ
    -0.59
    stadt
    -0.59
    redo
    -0.55
    itary
    -0.55
     Accessed
    -0.53
     subsequent
    -0.52
     unmarked
    -0.52
     doubtful
    -0.52
    amaz
    -0.51
    POSITIVE LOGITS
     into
    1.14
     with
    0.97
    into
    0.93
     seamlessly
    0.88
     together
    0.86
    with
    0.85
     onto
    0.82
     elements
    0.82
     genres
    0.79
     disparate
    0.78
    Activations Density 0.234%

    No Known Activations