© 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. 6-RES-JB
    11. 9247
    Prev
    Next
    INDEX
    Explanations

    informal language expressions including strong language and interrogative sentences

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory or emphatic statements

    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
     ..."
    -0.90
    .","
    -0.81
     �
    -0.76
     \"
    -0.74
     ('
    -0.70
     respectively
    -0.68
     [|
    -0.67
    \"
    -0.66
    "],"
    -0.65
     thereto
    -0.65
    POSITIVE LOGITS
    resa
    1.14
    odore
    1.10
    xiety
    1.08
    withstanding
    0.95
    notations
    0.86
    uckland
    0.83
    romeda
    0.82
    rary
    0.79
    aminer
    0.78
    icularly
    0.77
    Activations Density 0.507%

    No Known Activations