© 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. 2-RES-JB
    11. 17844
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person or place, likely related to the name "Cho"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cho" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doors
    -0.88
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
    dash
    -0.67
    Definition
    -0.66
    RANT
    -0.65
    FORMATION
    -0.63
    Reloaded
    -0.63
    night
    -0.63
    vae
    -0.62
    working
    -0.62
    POSITIVE LOGITS
    ices
    1.04
    oser
    1.02
    osing
    0.99
    oldown
    0.96
    pper
    0.95
    iral
    0.90
     Cho
    0.88
    iced
    0.88
    icer
    0.86
    pped
    0.85
    Activations Density 0.008%

    No Known Activations