© 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. 11-RES-JB
    11. 17666
    Prev
    Next
    INDEX
    Explanations

    mentions of sports team positions such as general manager

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in leadership positions within organizations, particularly general managers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.85
    ting
    -0.74
    tones
    -0.66
    cial
    -0.66
    bol
    -0.65
    ibly
    -0.64
    bang
    -0.64
    ulence
    -0.64
    staking
    -0.63
    keye
    -0.62
    POSITIVE LOGITS
     Manager
    0.76
     manager
    0.69
    manager
    0.62
     Selected
    0.58
     Admission
    0.58
    angled
    0.56
    addy
    0.56
     Mist
    0.56
     managers
    0.55
    Manager
    0.53
    Activations Density 0.152%

    No Known Activations