© 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. 23563
    Prev
    Next
    INDEX
    Explanations

    mentions of cell phones or related terminology

    oai_token-act-pair · gpt-3.5-turbo

    references to cell phones and their role in society

    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
     Lars
    -0.73
     Welch
    -0.68
    cru
    -0.68
     Larson
    -0.66
     Lep
    -0.66
     Hodg
    -0.65
     Stevens
    -0.64
    mary
    -0.63
    hillary
    -0.62
    chev
    -0.62
    POSITIVE LOGITS
    haar
    0.86
    arettes
    0.86
    phones
    0.74
     disorders
    0.70
     devices
    0.69
    uyomi
    0.69
     commerce
    0.68
    giene
    0.68
    ographers
    0.67
     Addiction
    0.67
    Activations Density 0.107%

    No Known Activations