© 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. 4091
    Prev
    Next
    INDEX
    Explanations

    instances of the word "already."

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

    instances of the word "already"

    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
    PDATE
    -1.13
    senal
    -1.12
     behavi
    -0.91
     srf
    -0.88
     practition
    -0.87
    CLASSIFIED
    -0.84
     adolesc
    -0.84
     subur
    -0.81
    Ą
    -0.80
    -0.80
    POSITIVE LOGITS
     begun
    1.30
     gotten
    1.21
     been
    1.21
     undergone
    1.19
     spoken
    1.15
     gone
    1.14
     taken
    1.12
     fallen
    1.11
     flown
    1.06
     risen
    1.06
    Activations Density 0.214%

    No Known Activations