© 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. 4-RES-JB
    11. 15306
    Prev
    Next
    INDEX
    Explanations

    words related to medical specialists in neurology

    oai_token-act-pair · gpt-3.5-turbo

    mentions of people associated with various professions or titles

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

    No Comments

    Negative Logits
    é¾
    -0.76
     maize
    -0.67
     Mirage
    -0.66
     Virtue
    -0.66
     gearing
    -0.64
     Parenthood
    -0.64
     Surviv
    -0.63
     lent
    -0.62
     Shed
    -0.61
     Garg
    -0.60
    POSITIVE LOGITS
    otle
    1.15
    orian
    1.08
    opher
    1.07
    ocrats
    1.06
    ocrat
    1.05
    ophe
    1.04
    inal
    0.95
    ocratic
    0.93
    obal
    0.92
    ically
    0.92
    Activations Density 0.008%

    No Known Activations