© 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. 9-RES-JB
    11. 18510
    Prev
    Next
    INDEX
    Explanations

    mentions of interviews or conversations with individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of interviews or discussions with individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    borgh
    -0.70
    yt
    -0.66
    ãĥĻ
    -0.65
    Interstitial
    -0.65
     endanger
    -0.65
    RGB
    -0.64
    âĶģ
    -0.63
    urn
    -0.62
     inflic
    -0.62
    HTML
    -0.62
    POSITIVE LOGITS
     knowledgeable
    0.91
     filmmaker
    0.84
     Professor
    0.81
     founder
    0.80
     representatives
    0.79
     longtime
    0.79
    Sources
    0.78
    creator
    0.77
     experts
    0.77
     author
    0.77
    Activations Density 0.169%

    No Known Activations