© 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. 10-RES-JB
    11. 6512
    Prev
    Next
    INDEX
    Explanations

    numerical values expressed in decimal format with high precision

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.66
    die
    -0.60
    etch
    -0.59
    ataka
    -0.57
    rollers
    -0.57
    ayers
    -0.56
    ayn
    -0.55
     preservation
    -0.55
     recre
    -0.55
     inval
    -0.55
    POSITIVE LOGITS
    -.
    1.12
    ohm
    0.99
    66666666
    0.89
    %,
    0.89
    %.
    0.89
    %
    0.88
    00000000
    0.86
    125
    0.83
    %"
    0.83
    %%
    0.82
    Activations Density 0.046%

    No Known Activations