© 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. 3676
    Prev
    Next
    INDEX
    Explanations

    professionals who hold specific titles, such as "associate professor" or "associate director"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' professional titles, particularly "associate" roles in academic or organizational contexts

    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
    Ö¼
    -0.85
    enegger
    -0.81
    =-=-=-=-=-=-=-=-
    -0.80
    cale
    -0.79
    atche
    -0.78
    worms
    -0.78
    stakes
    -0.77
    iders
    -0.76
    apo
    -0.75
    CRIP
    -0.74
    POSITIVE LOGITS
     dean
    0.91
     professor
    0.80
    lly
    0.79
     newsp
    0.79
     associate
    0.78
     Degree
    0.75
    rete
    0.71
    iate
    0.70
    uate
    0.69
    ociate
    0.68
    Activations Density 0.019%

    No Known Activations