© 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. 6-RES-JB
    11. 15012
    Prev
    Next
    INDEX
    Explanations

    references to praise or recognition, particularly in the form of standing ovations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "standing" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egu
    -0.78
    ilers
    -0.78
    iler
    -0.72
    TeX
    -0.71
    xy
    -0.71
    ffic
    -0.70
    hig
    -0.69
    EStream
    -0.69
    quer
    -0.68
    ocaly
    -0.68
    POSITIVE LOGITS
    still
    1.07
     upright
    0.84
     desks
    0.78
     ov
    0.75
    ances
    0.71
     tall
    0.70
     taller
    0.67
    outs
    0.66
    abouts
    0.64
     outdoors
    0.64
    Activations Density 0.012%

    No Known Activations