© 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. 15385
    Prev
    Next
    INDEX
    Explanations

    researchers and research-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Researchers."

    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
    BuyableInstoreAndOnline
    -0.74
    Enough
    -0.68
     ACTIONS
    -0.67
    icative
    -0.65
     Rapids
    -0.63
    nah
    -0.62
    AAAA
    -0.62
    times
    -0.61
     confrontation
    -0.60
    eful
    -0.59
    POSITIVE LOGITS
     studying
    1.05
    Researchers
    0.99
     Researchers
    0.99
     researchers
    0.94
     researching
    0.93
     specializing
    0.92
     researcher
    0.89
     probing
    0.88
    paces
    0.87
    hips
    0.87
    Activations Density 0.060%

    No Known Activations