© 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. 8-RES-JB
    11. 6159
    Prev
    Next
    INDEX
    Explanations

    references to economic indicators like gross domestic product (GDP)

    oai_token-act-pair · gpt-3.5-turbo

    references to economic terms, particularly those related to gross domestic product and gross national debt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attled
    -0.71
     Buckingham
    -0.66
    riages
    -0.64
    ournal
    -0.63
    FN
    -0.62
    pire
    -0.61
     therap
    -0.60
    orea
    -0.60
     Abbey
    -0.59
    helps
    -0.59
    POSITIVE LOGITS
    ewater
    0.91
     receipts
    0.90
    hest
    0.83
     disproportion
    0.78
     negligence
    0.76
    efully
    0.75
    es
    0.74
    oms
    0.74
    stal
    0.73
    cre
    0.71
    Activations Density 0.035%

    No Known Activations