© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9702
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals such as Kanye West and George Soros

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ial
    -0.95
    ional
    -0.91
    odic
    -0.88
    igi
    -0.73
    iotic
    -0.69
    iop
    -0.69
    ateral
    -0.67
    ively
    -0.66
    iership
    -0.66
    ents
    -0.65
    POSITIVE LOGITS
    zsche
    0.80
    rament
    0.78
    char
    0.71
    rup
    0.69
    Ĥ¬
    0.68
    nuts
    0.68
    orious
    0.67
    stad
    0.66
    ollen
    0.66
    lasses
    0.65
    Activations Density 0.058%

    No Known Activations