© 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. 3658
    Prev
    Next
    INDEX
    Explanations

    statements or actions related to reversal or changing directions

    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
    »Ĵ
    -0.74
    hyde
    -0.74
    uana
    -0.70
    TERN
    -0.69
    asia
    -0.69
    ulhu
    -0.68
    ittees
    -0.66
    lov
    -0.65
    ascus
    -0.65
    ividual
    -0.65
    POSITIVE LOGITS
     course
    1.03
     decades
    0.94
     Roe
    0.94
     longstanding
    0.88
     Course
    0.85
     centuries
    0.84
     previous
    0.83
     fortunes
    0.83
     convictions
    0.82
     rulings
    0.81
    Activations Density 0.138%

    No Known Activations