© 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. 17167
    Prev
    Next
    INDEX
    Explanations

    phrases related to various projects and initiatives across different fields

    oai_token-act-pair · gpt-3.5-turbo

    active involvement in community service initiatives

    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
     constitu
    -0.73
    fuck
    -0.73
    ghazi
    -0.71
    reply
    -0.66
    whatever
    -0.64
    iatus
    -0.63
     panicked
    -0.62
    fix
    -0.61
    Conservative
    -0.61
     decency
    -0.61
    POSITIVE LOGITS
    quartered
    1.02
     motto
    0.87
     dedication
    0.76
    eaturing
    0.76
     Features
    0.72
     impressive
    0.72
     accol
    0.72
     Included
    0.71
     inspir
    0.70
    ounded
    0.69
    Activations Density 0.618%

    No Known Activations