© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17426
    Prev
    Next
    INDEX
    Explanations

    names or references to a person named Jermaine

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Jer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     screened
    -0.67
     magnification
    -0.60
     giants
    -0.60
     Ducks
    -0.60
     divided
    -0.58
    holders
    -0.56
    holder
    -0.55
     Neurolog
    -0.55
     microscope
    -0.55
     populous
    -0.55
    POSITIVE LOGITS
    seys
    1.47
    usalem
    1.38
    miah
    1.27
    icho
    1.13
    ilyn
    1.07
    boa
    1.02
    usha
    1.01
    sey
    0.95
    obo
    0.94
    king
    0.90
    Activations Density 0.011%

    No Known Activations