© 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. 2-RES-JB
    11. 1407
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations

    oai_token-act-pair · gpt-3.5-turbo

    references to business or organizational operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknowled
    -0.73
    gets
    -0.64
    clud
    -0.61
    udd
    -0.61
    agle
    -0.60
    vae
    -0.60
    bitious
    -0.59
    Entry
    -0.59
    latest
    -0.59
    Half
    -0.59
    POSITIVE LOGITS
     operations
    0.94
     operation
    0.86
    chwitz
    0.85
    operation
    0.78
    WER
    0.78
    hell
    0.74
    aution
    0.73
     operative
    0.73
     Operations
    0.71
     operators
    0.70
    Activations Density 0.012%

    No Known Activations