© 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. 8-RES-JB
    11. 6842
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific locations or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Wood."

    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
    ional
    -0.85
    uates
    -0.73
    uated
    -0.73
     disenfranch
    -0.70
     aver
    -0.69
    uate
    -0.68
    BILITY
    -0.68
    OPLE
    -0.66
     disguise
    -0.66
    itia
    -0.66
    POSITIVE LOGITS
    ruff
    1.43
    stock
    1.13
    working
    1.12
    cock
    1.11
    bridge
    1.10
    lands
    1.09
    lake
    1.07
    cutting
    1.05
    leigh
    1.03
    row
    1.03
    Activations Density 0.022%

    No Known Activations