© 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. 6-RES-JB
    11. 7884
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronic devices and systems

    oai_token-act-pair · gpt-3.5-turbo

    product names and associated specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agher
    -0.69
    unders
    -0.66
    grass
    -0.65
     è£ıè¦ļéĨĴ
    -0.63
    lay
    -0.61
    Semitism
    -0.61
    =]
    -0.61
    acci
    -0.60
    tackle
    -0.60
    rossover
    -0.59
    POSITIVE LOGITS
     suffers
    0.72
     ENT
    0.69
     invent
    0.68
     Odyssey
    0.67
     designers
    0.66
     PD
    0.65
    orno
    0.63
     manufactures
    0.62
     pH
    0.61
     physic
    0.61
    Activations Density 1.058%

    No Known Activations