© 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. 1-RES-JB
    11. 17370
    Prev
    Next
    INDEX
    Explanations

    phrases related to acquiring or obtaining something

    oai_token-act-pair · gpt-3.5-turbo

    words related to purchasing or acquiring items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ambient
    -0.64
    ographers
    -0.61
     Blazers
    -0.61
     accompanying
    -0.60
    Jordan
    -0.59
    idity
    -0.59
     choking
    -0.58
     Tart
    -0.58
     throat
    -0.56
     majesty
    -0.56
    POSITIVE LOGITS
    ought
    1.13
    nesday
    0.95
    ynes
    0.93
    \\\\\\\\
    0.89
    sburgh
    0.85
    sburg
    0.84
    irit
    0.81
    endment
    0.81
    undle
    0.81
    ratulations
    0.80
    Activations Density 0.004%

    No Known Activations