© 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. 1-RES-JB
    11. 24176
    Prev
    Next
    INDEX
    Explanations

    locations or places, particularly with the word "Market"

    oai_token-act-pair · gpt-3.5-turbo

    references to marketplaces or market locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.88
    20439
    -0.69
    ÑĮ
    -0.67
    netflix
    -0.66
    teness
    -0.65
    aho
    -0.64
    åĤ
    -0.63
    ALSE
    -0.62
    ran
    -0.59
    said
    -0.59
    POSITIVE LOGITS
    Market
    1.06
     Market
    0.97
    places
    0.95
    eers
    0.92
     Markets
    0.85
    markets
    0.80
    hare
    0.79
    anke
    0.76
    Trade
    0.76
    Watch
    0.76
    Activations Density 0.014%

    No Known Activations