© 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. 10-RES-JB
    11. 4828
    Prev
    Next
    INDEX
    Explanations

    instances where something is being removed or taken down

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eele
    -0.75
    inar
    -0.70
    imity
    -0.70
    arser
    -0.69
    eln
    -0.68
    tains
    -0.67
    zen
    -0.66
    erest
    -0.66
    aval
    -0.65
    hov
    -0.65
    POSITIVE LOGITS
     replaced
    1.09
     leaving
    1.05
     albeit
    1.02
     prompting
    0.90
     citing
    0.90
     presumably
    0.90
     meaning
    0.89
     but
    0.89
     however
    0.87
     although
    0.87
    Activations Density 0.329%

    No Known Activations