© 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. 12139
    Prev
    Next
    INDEX
    Explanations

    the name "Norm" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly those related to specific individuals and events

    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
    uates
    -0.80
    tered
    -0.76
    heit
    -0.75
    bats
    -0.71
     "$:/
    -0.67
    quez
    -0.66
    Rush
    -0.66
    warts
    -0.66
    FFER
    -0.65
    inventoryQuantity
    -0.64
    POSITIVE LOGITS
     disadvant
    0.79
    inals
    0.75
    resso
    0.75
     Norm
    0.75
    foundland
    0.74
    verages
    0.67
    efficients
    0.66
     Palestin
    0.65
    ality
    0.65
    entric
    0.65
    Activations Density 0.031%

    No Known Activations