© 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. 4-RES-JB
    11. 4749
    Prev
    Next
    INDEX
    Explanations

    words related to speed or quickness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "quick" in various contexts

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

    No Comments

    Negative Logits
    âĹ¼
    -0.82
    ichick
    -0.75
    Ãį
    -0.70
     Seah
    -0.69
    obyl
    -0.69
    INA
    -0.68
    çĶ°
    -0.66
    ickson
    -0.66
     Katz
    -0.65
    inian
    -0.64
    POSITIVE LOGITS
    ened
    1.03
     turnaround
    1.02
     succession
    1.00
    ening
    0.99
    aneously
    0.98
    itude
    0.97
    lime
    0.92
     enough
    0.89
    eners
    0.86
    fix
    0.86
    Activations Density 0.019%

    No Known Activations