© 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. 1084
    Prev
    Next
    INDEX
    Explanations

    text related to various individuals, countries, and entities

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and proper nouns related to specific individuals or organizations

    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
     skelet
    -0.72
    tesy
    -0.63
     arrang
    -0.62
     Engels
    -0.61
    atform
    -0.60
    ITNESS
    -0.59
    mouse
    -0.59
    ¥ŀ
    -0.59
     slightest
    -0.58
    OOD
    -0.56
    POSITIVE LOGITS
    pta
    1.01
    letal
    0.87
    ificant
    0.87
    orf
    0.81
    oslav
    0.75
    atchewan
    0.74
    uous
    0.74
    eper
    0.73
    士
    0.71
    utsche
    0.68
    Activations Density 0.529%

    No Known Activations