© 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. 7-RES-JB
    11. 20690
    Prev
    Next
    INDEX
    Explanations

    JSON key-value pairs

    oai_token-act-pair · gpt-3.5-turbo

    structured data fields and identifiers typical in coding or data representation contexts

    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
    ulty
    -0.86
    estones
    -0.79
    iculty
    -0.76
    omorphic
    -0.75
    iband
    -0.70
    utive
    -0.69
    emouth
    -0.69
    ebus
    -0.68
    izards
    -0.68
    mma
    -0.68
    POSITIVE LOGITS
    null
    1.16
     null
    1.07
     NULL
    0.97
     false
    0.94
     {"
    0.94
     [];
    0.93
     undefined
    0.93
     False
    0.89
     None
    0.88
     nil
    0.87
    Activations Density 0.029%

    No Known Activations