© 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. 7-RES-JB
    11. 9595
    Prev
    Next
    INDEX
    Explanations

    words related to expressing support or agreement

    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
    anus
    -0.76
     Gap
    -0.71
    enegger
    -0.71
    anned
    -0.68
     typo
    -0.67
    kefeller
    -0.63
     Brist
    -0.60
    uilt
    -0.59
     Gorge
    -0.58
     Shant
    -0.57
    POSITIVE LOGITS
    itism
    0.91
    clusion
    0.74
     thereof
    0.72
    iveness
    0.71
    porting
    0.69
    anding
    0.68
    raints
    0.67
    cussion
    0.67
    clude
    0.66
    ative
    0.66
    Activations Density 0.033%

    No Known Activations