© 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. 4-RES-JB
    11. 20526
    Prev
    Next
    INDEX
    Explanations

    phrases related to distances or measurements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nautical measurements and specifications

    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
    gren
    -0.80
    ivism
    -0.71
    overs
    -0.68
    ioned
    -0.68
    ividual
    -0.68
    iang
    -0.67
    oter
    -0.66
    ees
    -0.66
     Karin
    -0.65
    ion
    -0.65
    POSITIVE LOGITS
    autical
    1.35
    cean
    0.87
    andise
    0.78
    ¢
    0.78
     precision
    0.72
    ¦
    0.72
     actionGroup
    0.71
    foundland
    0.70
    mph
    0.70
    Ń·
    0.70
    Activations Density 0.023%

    No Known Activations