© 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. 12952
    Prev
    Next
    INDEX
    Explanations

    phrases related to work crews and operations

    oai_token-act-pair · gpt-3.5-turbo

    references to work teams or groups involved in specific tasks or jobs

    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
    ebook
    -0.69
     Amendments
    -0.66
    lier
    -0.66
    zai
    -0.66
    Viol
    -0.65
    Georg
    -0.64
    ENC
    -0.63
    mobi
    -0.63
    MED
    -0.62
     Hus
    -0.62
    POSITIVE LOGITS
     crews
    1.18
     redes
    0.92
     crew
    0.84
    uggest
    0.84
    ynthesis
    0.81
    mith
    0.81
    ignty
    0.81
    chwitz
    0.81
    dayName
    0.81
    paces
    0.78
    Activations Density 0.011%

    No Known Activations