© 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. 4-RES-JB
    11. 3698
    Prev
    Next
    INDEX
    Explanations

    the name "Darrell," especially with variations in spelling

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and brands

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

    No Comments

    Negative Logits
    bered
    -0.82
    racted
    -0.68
    STER
    -0.66
    oho
    -0.66
    Ħ¢
    -0.65
    ding
    -0.64
    ials
    -0.61
    ber
    -0.60
     fisher
    -0.60
     srf
    -0.59
    POSITIVE LOGITS
    Reviewer
    0.96
    aimon
    0.92
    hurst
    0.81
    ghazi
    0.79
    iquid
    0.75
    ãģĦ
    0.75
    Sham
    0.74
    Evil
    0.73
    اÙĦ
    0.70
    Constructed
    0.69
    Activations Density 0.029%

    No Known Activations