© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20687
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers separated by commas

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to measurements

    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
    abase
    -0.85
    abeth
    -0.75
    ata
    -0.75
    heit
    -0.72
    wagen
    -0.70
    escription
    -0.69
     veter
    -0.67
    ĸļ
    -0.66
    resa
    -0.64
    hes
    -0.64
    POSITIVE LOGITS
     teaspoons
    0.86
     GHz
    0.85
    BuyableInstoreAndOnline
    0.81
    66666666
    0.80
    GHz
    0.78
    elsius
    0.77
     tablespoons
    0.76
     ILCS
    0.75
    adra
    0.74
    000
    0.74
    Activations Density 1.436%

    No Known Activations