© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1078
    Prev
    Next
    INDEX
    Explanations

    terms related to professionals or job titles, such as teachers, doctors, and bankers

    oai_token-act-pair · gpt-3.5-turbo

    connections and cooperative relationships between individuals or groups

    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
     Invasion
    -0.75
    ONSORED
    -0.70
    ukong
    -0.68
    bia
    -0.68
    philis
    -0.68
    mia
    -0.68
    icity
    -0.68
    ishment
    -0.67
    itability
    -0.66
    arez
    -0.65
    POSITIVE LOGITS
     technicians
    1.18
     educators
    1.13
     managers
    1.12
     bureaucrats
    1.10
     assistants
    1.10
     engineers
    1.08
     distributors
    1.08
     therapists
    1.07
     directors
    1.05
     performers
    1.04
    Activations Density 0.327%

    No Known Activations