© 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. 803
    Prev
    Next
    INDEX
    Explanations

    mentions of famous or noteworthy individuals or personalities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of notable individuals and their status or achievements

    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
    oxic
    -0.64
     degraded
    -0.63
    REDACTED
    -0.63
     afterwards
    -0.59
    Viol
    -0.58
     Worse
    -0.58
     deterior
    -0.57
    destroy
    -0.57
    violence
    -0.56
     inflicted
    -0.56
    POSITIVE LOGITS
     excitement
    0.84
     fascination
    0.77
     sighting
    0.77
     coincidence
    0.74
     sightings
    0.72
     trivia
    0.71
     inspiration
    0.70
    fetched
    0.68
     intrigued
    0.67
     inspir
    0.66
    Activations Density 1.273%

    No Known Activations