© 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. 8-RES-JB
    11. 2605
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with academic titles such as "Professor" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of academic titles or roles, specifically "Professor."

    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
     destro
    -0.89
     routed
    -0.74
     ranger
    -0.69
     compr
    -0.68
     queen
    -0.66
     rebound
    -0.66
    leased
    -0.64
    OPA
    -0.64
     avalanche
    -0.63
     skelet
    -0.61
    POSITIVE LOGITS
    essors
    1.28
     Hawking
    1.14
     Laure
    0.96
     Dawkins
    0.92
     Stephen
    0.89
     Richard
    0.87
     Kelvin
    0.87
     Andrew
    0.84
     Nigel
    0.83
     Michel
    0.83
    Activations Density 0.020%

    No Known Activations