© 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. 12153
    Prev
    Next
    INDEX
    Explanations

    mentions of social classes, particularly the middle class

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the middle class

    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
    inventoryQuantity
    -0.71
     porous
    -0.69
    WAYS
    -0.65
     sexually
    -0.63
    nown
    -0.62
     commercially
    -0.62
     controversial
    -0.62
    vernment
    -0.61
    catch
    -0.60
    sites
    -0.60
    POSITIVE LOGITS
    ifications
    0.86
    class
    0.80
    alion
    0.80
    ifiers
    0.80
    ifier
    0.77
    hesis
    0.76
     class
    0.76
    dinand
    0.75
    geist
    0.74
    ifying
    0.73
    Activations Density 0.017%

    No Known Activations