© 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. 6-RES-JB
    11. 7819
    Prev
    Next
    INDEX
    Explanations

    capital letters with non-alphabet characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or actions that indicate critical moments or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.71
    abouts
    -0.66
     endeavour
    -0.64
     Thornton
    -0.63
     Ferdinand
    -0.61
    hene
    -0.61
     brunt
    -0.60
    anium
    -0.60
     enrol
    -0.59
     emancipation
    -0.59
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.98
    SCP
    0.83
    ³³³³³³³³
    0.83
    Ingredients
    0.83
    https
    0.82
    Liter
    0.81
    Looks
    0.80
    WARNING
    0.80
    ³³³³
    0.78
    Feature
    0.78
    Activations Density 0.135%

    No Known Activations