© 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. 9-RES-JB
    11. 4095
    Prev
    Next
    INDEX
    Explanations

    the word "to"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "seems to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.76
    bats
    -0.73
    opens
    -0.68
    rieved
    -0.66
    cart
    -0.65
    estern
    -0.65
    GGGGGGGG
    -0.65
    blooded
    -0.61
    leanor
    -0.61
    ashes
    -0.60
    POSITIVE LOGITS
     embody
    1.00
     imply
    0.98
     equate
    0.95
     indicate
    0.95
     contradict
    0.94
     be
    0.93
     defy
    0.91
     have
    0.88
     originate
    0.88
     specialize
    0.88
    Activations Density 0.072%

    No Known Activations