© 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. 23705
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong work ethics and personal qualities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to work ethic, advocacy, and creativity

    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
    GROUP
    -0.78
    vier
    -0.72
    ivably
    -0.70
    malink
    -0.67
     Fein
    -0.66
     ourselves
    -0.66
     PLEASE
    -0.65
    enstein
    -0.65
    cer
    -0.64
     STEP
    -0.64
    POSITIVE LOGITS
     antics
    1.06
     prowess
    1.04
     qualities
    0.99
    fulness
    0.99
     knack
    0.98
     skills
    0.94
     dedication
    0.94
     versatility
    0.94
     charisma
    0.93
     stunts
    0.92
    Activations Density 0.338%

    No Known Activations