© 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. 8-RES-JB
    11. 17702
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or positioning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to location and locational identifiers

    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
    child
    -0.87
    manship
    -0.83
    PDATE
    -0.74
    deen
    -0.68
    ħĭ
    -0.67
    uyomi
    -0.67
    jong
    -0.67
    gui
    -0.66
    NetMessage
    -0.63
    FactoryReloaded
    -0.62
    POSITIVE LOGITS
    ator
    1.02
    ally
    1.02
    abulary
    0.97
    atell
    0.97
    ality
    0.96
    ocity
    0.95
    entric
    0.91
    utor
    0.88
    ution
    0.86
    omorph
    0.86
    Activations Density 0.051%

    No Known Activations