Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4628
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a current stage of activity or progress

    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
     boobs
    -0.68
     Soldiers
    -0.67
     Sands
    -0.65
    by
    -0.64
     BaseType
    -0.64
    »Ĵ
    -0.63
    gans
    -0.59
    bey
    -0.58
    ById
    -0.58
     Pixie
    -0.57
    POSITIVE LOGITS
    ching
    1.11
     talks
    1.04
     charge
    0.96
     discussions
    0.94
     unch
    0.90
     negotiations
    0.90
     agreement
    0.89
     touch
    0.89
     favor
    0.89
     contention
    0.88
    Activations Density 0.089%

    No Known Activations