© 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. 23032
    Prev
    Next
    INDEX
    Explanations

    phrases related to doing a good job or job performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the performance of individuals or entities in various contexts

    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
    anism
    -0.77
     Izan
    -0.71
    coins
    -0.67
     instructions
    -0.67
    aneously
    -0.67
    evidence
    -0.64
    ateurs
    -0.64
     americ
    -0.63
    items
    -0.62
    things
    -0.62
    POSITIVE LOGITS
     lot
    1.17
     whopping
    1.11
     tremendous
    1.05
     plethora
    1.02
     slew
    0.99
     considerable
    0.97
     huge
    0.96
     resurgence
    0.94
     terrific
    0.93
     remarkable
    0.92
    Activations Density 0.289%

    No Known Activations