© 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. 9-RES-JB
    11. 20696
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations, particularly related to marketplaces

    oai_token-act-pair · gpt-3.5-turbo

    references to markets and market-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĤ
    -0.74
    aho
    -0.69
    said
    -0.69
    netflix
    -0.66
    bernatorial
    -0.65
     Fas
    -0.64
     Alleg
    -0.64
     Ath
    -0.63
    udes
    -0.63
     Lak
    -0.62
    POSITIVE LOGITS
    places
    1.60
    eers
    1.41
    eer
    1.22
    hare
    1.12
    eering
    1.06
    place
    1.00
     Reloaded
    0.85
     fluctuations
    0.79
     downturn
    0.79
     prices
    0.76
    Activations Density 0.042%

    No Known Activations