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

    Neuronpedia

    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. 1-RES-JB
    11. 5287
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority figures or roles

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal or authoritative positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psc
    -0.68
    ©
    -0.68
     coarse
    -0.66
    tra
    -0.64
    åĮ
    -0.63
    printf
    -0.62
    follow
    -0.60
    é¾
    -0.60
    ·
    -0.60
     Paleo
    -0.59
    POSITIVE LOGITS
    itor
    1.64
    itors
    1.42
    ious
    1.07
    ial
    0.96
    ority
    0.93
    maid
    0.88
    ium
    0.88
    abase
    0.87
    itance
    0.86
    iors
    0.85
    Activations Density 0.006%

    No Known Activations