© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7130
    Prev
    Next
    INDEX
    Explanations

    questions or statements containing contractions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortunately
    -0.91
     withd
    -0.86
     exha
    -0.83
     rall
    -0.82
     newcom
    -0.78
    anwhile
    -0.78
     eleph
    -0.74
    Þ
    -0.71
     exting
    -0.71
     confir
    -0.70
    POSITIVE LOGITS
    't
    1.67
    ny
    0.92
    ovan
    0.90
    ada
    0.87
    ÃŃ
    0.86
    ned
    0.78
    athan
    0.78
    ALD
    0.77
    thia
    0.77
    na
    0.77
    Activations Density 0.055%

    No Known Activations