© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 20626
    Prev
    Next
    INDEX
    Explanations

    locations and settings

    oai_token-act-pair · gpt-3.5-turbo

    locations and settings relevant to narrative descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    letes
    -0.80
    ogether
    -0.79
    ticket
    -0.68
     projectiles
    -0.68
    aterial
    -0.66
     pledges
    -0.63
    stood
    -0.62
    gered
    -0.62
     recipients
    -0.62
    cknow
    -0.61
    POSITIVE LOGITS
     circa
    1.11
     somewhere
    0.98
     overlooking
    0.97
     countryside
    0.94
     northwest
    0.92
     sunny
    0.92
     tucked
    0.92
     suburb
    0.90
     surrounded
    0.86
     Somewhere
    0.85
    Activations Density 0.509%

    No Known Activations