© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4548
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing a strong opinion or urgent call to action

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the word "There" in various contexts, indicating the presence of information or facts being stated

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     comprom
    -0.54
     afar
    -0.52
     IPM
    -0.51
     prelim
    -0.50
     nib
    -0.50
     Ashes
    -0.50
    ointed
    -0.49
     sacrific
    -0.49
     whipping
    -0.47
     caffe
    -0.47
    POSITIVE LOGITS
    after
    1.25
    upon
    1.07
    by
    1.03
    fore
    1.02
    FORE
    0.96
     are
    0.89
     exists
    0.87
    for
    0.83
    osate
    0.82
    in
    0.81
    Activations Density 0.108%

    No Known Activations