© 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. 10-RES-JB
    11. 17281
    Prev
    Next
    INDEX
    Explanations

    positions or roles held by individuals in various institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "served as" followed by a role or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrs
    -0.91
    tons
    -0.70
    ech
    -0.69
    isphere
    -0.69
    isable
    -0.68
    ecd
    -0.68
    itiveness
    -0.66
    asy
    -0.66
    ueller
    -0.65
    oche
    -0.64
    POSITIVE LOGITS
     assistant
    1.25
     director
    1.20
     chairman
    1.20
     Assistant
    1.20
     deputy
    1.19
     interim
    1.16
     Director
    1.15
     Managing
    1.10
     coordinator
    1.09
     CEO
    1.09
    Activations Density 0.086%

    No Known Activations