© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23664
    Prev
    Next
    INDEX
    Explanations

    words related to starting or creating something from the beginning

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to creating or building something from the ground up

    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
    quickShipAvailable
    -0.78
    agonist
    -0.77
     Osw
    -0.75
    CVE
    -0.75
    rid
    -0.70
    acl
    -0.66
    uned
    -0.66
    anchester
    -0.65
    agements
    -0.64
    anamo
    -0.64
    POSITIVE LOGITS
     scratch
    1.02
     scratched
    0.89
    manship
    0.84
    pad
    0.81
     slate
    0.79
    book
    0.78
    bones
    0.77
    eting
    0.76
    beat
    0.74
    backer
    0.72
    Activations Density 0.026%

    No Known Activations