© 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. 9902
    Prev
    Next
    INDEX
    Explanations

    notions of potential, significance, and solutions within different contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with clean energy solutions and opportunities

    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
    mares
    -0.76
    rief
    -0.72
    ichen
    -0.69
    bara
    -0.66
    atted
    -0.64
     varies
    -0.64
     Nightmares
    -0.64
     Chatt
    -0.62
    tails
    -0.61
    ttle
    -0.60
    POSITIVE LOGITS
     savior
    1.14
     potential
    1.04
     imminent
    1.02
     pinnacle
    0.95
     successor
    0.94
     threat
    0.94
     preferable
    0.92
     promising
    0.92
     viable
    0.91
     antidote
    0.90
    Activations Density 0.229%

    No Known Activations