© 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. 9-RES-JB
    11. 4879
    Prev
    Next
    INDEX
    Explanations

    phrases related to specialization or specific expertise

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specialization and expertise in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¥
    -0.79
    down
    -0.77
    runner
    -0.76
    sburg
    -0.76
    bow
    -0.76
    antine
    -0.73
    downs
    -0.72
    runners
    -0.71
    ãĤ§
    -0.69
    tight
    -0.65
    POSITIVE LOGITS
    ategor
    0.87
     specialize
    0.84
     specializes
    0.81
     specialized
    0.79
     specialization
    0.77
    kson
    0.76
     locality
    0.75
    opath
    0.74
     Excellence
    0.74
     servicing
    0.74
    Activations Density 0.089%

    No Known Activations