© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 10373
    Prev
    Next
    INDEX
    Explanations

    instances of the word "layer" and assign high activation values to any numerical values associated with it

    oai_token-act-pair · gpt-3.5-turbo

    references to layers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    date
    -0.71
    ICES
    -0.66
     Predators
    -0.64
    orth
    -0.64
     Scand
    -0.63
    transform
    -0.63
    Latin
    -0.63
    speaking
    -0.63
     STAR
    -0.62
    opened
    -0.61
    POSITIVE LOGITS
     layer
    1.50
     layers
    1.46
    layer
    1.24
    Layer
    1.24
     Layer
    1.20
     layered
    0.86
    ayers
    0.84
     thickness
    0.83
     coats
    0.78
    htaking
    0.77
    Activations Density 0.008%

    No Known Activations