© 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. 16775
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named "Jones"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "Jones."

    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
    racted
    -0.88
    aneously
    -0.87
    ULAR
    -0.85
    uated
    -0.84
    ulatory
    -0.78
    aneous
    -0.77
    utive
    -0.77
    rous
    -0.72
    zes
    -0.70
    uate
    -0.70
    POSITIVE LOGITS
    sey
    1.07
    boro
    1.06
    hof
    0.83
    haw
    0.83
    hole
    0.80
     Jr
    0.75
    heng
    0.75
    cott
    0.74
    Jones
    0.74
    borough
    0.74
    Activations Density 0.041%

    No Known Activations