© 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. 2757
    Prev
    Next
    INDEX
    Explanations

    terms related to different levels of government, such as national, state, federal, and local

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different levels of governance and organization

    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
    terday
    -0.88
    atism
    -0.73
    acted
    -0.66
    olia
    -0.65
    Operation
    -0.64
    Weather
    -0.64
    thens
    -0.62
    lication
    -0.60
    DragonMagazine
    -0.59
    uria
    -0.59
    POSITIVE LOGITS
     level
    1.23
     doorstep
    1.23
     stage
    1.19
     podium
    1.18
     aisle
    1.15
     shores
    1.13
     horizon
    1.11
     throne
    1.10
     periphery
    1.09
     fray
    1.09
    Activations Density 0.240%

    No Known Activations