© 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. 4904
    Prev
    Next
    INDEX
    Explanations

    phrases related to hierarchy or ranking

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "order of" followed by a number

    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
    gae
    -0.80
    gre
    -0.77
    owler
    -0.71
    hoe
    -0.71
    gow
    -0.70
    culosis
    -0.69
    atten
    -0.69
    touch
    -0.68
    stock
    -0.67
    ished
    -0.65
    POSITIVE LOGITS
    SpaceEngineers
    0.78
    MX
    0.76
     approvals
    0.74
     deletion
    0.70
    execute
    0.69
    ©¶æ
    0.67
     dissolution
    0.67
     visitation
    0.66
     ACTIONS
    0.66
     execution
    0.66
    Activations Density 0.292%

    No Known Activations