© 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. 3908
    Prev
    Next
    INDEX
    Explanations

    phrases related to construction or digging in the earth

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

    phrases indicating locations or positions

    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
     reconnect
    -0.66
     Ahead
    -0.61
     whereabouts
    -0.61
     ahead
    -0.61
     elector
    -0.61
     hes
    -0.60
     redistributed
    -0.59
    ................................
    -0.58
    iety
    -0.58
    encer
    -0.57
    POSITIVE LOGITS
    neath
    1.22
    cooked
    1.15
    foot
    1.14
    pants
    1.13
    growth
    1.13
    stated
    1.04
    gar
    1.03
    sea
    1.02
    brush
    1.00
    developed
    0.97
    Activations Density 0.051%

    No Known Activations