© 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. 8-RES-JB
    11. 4178
    Prev
    Next
    INDEX
    Explanations

    words related to legal matters and court cases

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to specific events or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.64
    Template
    -0.53
    Gra
    -0.53
     accord
    -0.53
    Ware
    -0.53
     Rodrig
    -0.52
    Category
    -0.51
    cture
    -0.51
    ifice
    -0.51
    agra
    -0.51
    POSITIVE LOGITS
     alike
    0.84
     thereof
    0.79
     thereafter
    0.69
     respectively
    0.66
     consequ
    0.64
    htm
    0.61
     thereto
    0.59
    zbollah
    0.57
    )!
    0.56
    cellaneous
    0.56
    Activations Density 0.313%

    No Known Activations