© 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. 11068
    Prev
    Next
    INDEX
    Explanations

    titles or roles related to leadership positions, such as president, CEO, executive director

    oai_token-act-pair · gpt-3.5-turbo

    titles related to positions of authority or leadership

    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
     stret
    -0.71
     \'
    -0.66
     verbs
    -0.63
     strangers
    -0.62
     lazy
    -0.58
     blat
    -0.57
     fools
    -0.56
     envy
    -0.55
     disgrace
    -0.55
     passage
    -0.55
    POSITIVE LOGITS
     emer
    1.00
     of
    0.94
    veland
    0.86
    director
    0.79
     managing
    0.79
     director
    0.75
    wark
    0.73
     Emer
    0.72
    exec
    0.71
    founder
    0.71
    Activations Density 0.068%

    No Known Activations