© 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 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. 7-RES-JB
    11. 24028
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Hadley."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Halley."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icion
    -0.86
    ilers
    -0.83
    glers
    -0.81
    utenberg
    -0.80
    icans
    -0.79
    umers
    -0.77
    illary
    -0.77
    dayName
    -0.76
    atform
    -0.75
    ãĥķãĤ©
    -0.74
    POSITIVE LOGITS
    wine
    1.00
    bridge
    0.98
    wood
    0.90
    rand
    0.85
    dale
    0.84
    corn
    0.83
    fleet
    0.81
     Hath
    0.80
    sburg
    0.80
    brook
    0.78
    Activations Density 0.037%

    No Known Activations