© 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. 11-RES-JB
    11. 18679
    Prev
    Next
    INDEX
    Explanations

    instances of locations or businesses opening or being established

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the opening of new establishments or facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecd
    -0.67
     constitu
    -0.67
    Serial
    -0.63
    Hide
    -0.62
     mathemat
    -0.62
    Continue
    -0.61
    govtrack
    -0.61
    hov
    -0.61
    eros
    -0.61
    arse
    -0.60
    POSITIVE LOGITS
     doors
    1.07
     its
    0.89
     up
    0.88
    ource
    0.81
     shop
    0.79
     Doors
    0.78
     shops
    0.77
     stores
    0.75
    tered
    0.75
     gates
    0.73
    Activations Density 0.061%

    No Known Activations