© 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. 12142
    Prev
    Next
    INDEX
    Explanations

    organizations or institutions where people work

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to job titles and employment history

    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
     poss
    -0.70
    zyk
    -0.70
     bree
    -0.69
    pmwiki
    -0.67
    oes
    -0.67
    æĦ
    -0.66
    quel
    -0.64
    Magikarp
    -0.64
    heim
    -0.62
    idd
    -0.61
    POSITIVE LOGITS
     Lockheed
    1.00
     Exxon
    0.97
     Goldman
    0.94
     consultancy
    0.94
     Hew
    0.93
     JPMorgan
    0.93
     IBM
    0.91
     Fortune
    0.87
     nonprofits
    0.87
     Dell
    0.87
    Activations Density 0.152%

    No Known Activations