© 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. 1-RES-JB
    11. 13510
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Greg" with the number 9 or 10 attached

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Greg."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -1.01
    pmwiki
    -0.78
    netflix
    -0.74
    cffffcc
    -0.74
    views
    -0.69
    appiness
    -0.67
    notice
    -0.66
    draft
    -0.65
    dream
    -0.65
    seeing
    -0.63
    POSITIVE LOGITS
    arious
    1.26
    orius
    1.10
    orio
    1.08
    Greg
    1.06
     Greg
    1.05
    orian
    0.99
    antine
    0.94
     Gian
    0.90
     Gregory
    0.89
    orem
    0.89
    Activations Density 0.007%

    No Known Activations