© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 9555
    Prev
    Next
    INDEX
    Explanations

    titles or positions related to leadership roles

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "and" along with titles of CEOs and executives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acci
    -0.74
    ivia
    -0.72
    asions
    -0.72
    ibly
    -0.71
    nia
    -0.70
    places
    -0.70
    arettes
    -0.67
    antically
    -0.67
    utic
    -0.67
    facts
    -0.67
    POSITIVE LOGITS
     CEO
    0.90
     Publisher
    0.77
     chief
    0.76
     foremost
    0.75
     namesake
    0.73
     Chief
    0.73
     daughter
    0.71
    CEO
    0.70
     Treasurer
    0.69
     treasurer
    0.69
    Activations Density 0.071%

    No Known Activations