© 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. 8550
    Prev
    Next
    INDEX
    Explanations

    the word "ite" with varying activation values

    oai_token-act-pair · gpt-3.5-turbo
    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
    ington
    -0.91
    INGTON
    -0.87
    ood
    -0.85
    nut
    -0.82
    nuts
    -0.81
    wards
    -0.80
    noon
    -0.77
    SIGN
    -0.75
    loo
    -0.74
     NCT
    -0.73
    POSITIVE LOGITS
    chnology
    1.26
    lli
    1.23
    geist
    0.95
    llo
    0.83
    lla
    0.83
    eer
    0.77
    gregation
    0.75
    chn
    0.74
     Scotia
    0.73
    xt
    0.72
    Activations Density 0.045%

    No Known Activations