© 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. 16391
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms, including numbers, currencies, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and statistics related to economics and job markets

    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
    antine
    -0.73
     Shack
    -0.60
    yip
    -0.60
    multiple
    -0.59
    atories
    -0.58
    Bomb
    -0.57
     toxicity
    -0.56
     endlessly
    -0.56
    izoph
    -0.55
    bard
    -0.55
    POSITIVE LOGITS
     compared
    0.82
     versus
    0.79
     vs
    0.79
     (-
    0.75
     registrations
    0.74
     tallied
    0.74
     (+
    0.72
     edged
    0.69
     recorded
    0.69
    ross
    0.67
    Activations Density 0.223%

    No Known Activations