© 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. 2-RES-JB
    11. 2488
    Prev
    Next
    INDEX
    Explanations

    stories or narratives

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "tales" or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.96
    erate
    -0.86
    gettable
    -0.79
    ournal
    -0.79
    ussy
    -0.76
    lav
    -0.75
    edient
    -0.75
    itter
    -0.74
    inyl
    -0.74
    foreseen
    -0.74
    POSITIVE LOGITS
     tales
    1.32
     tale
    1.27
     Tale
    1.01
     Tales
    1.00
    tale
    0.91
    tell
    0.84
     Reincarn
    0.84
     Ragnarok
    0.80
    fare
    0.80
     imagin
    0.72
    Activations Density 0.017%

    No Known Activations