© 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. 2-RES-JB
    11. 13537
    Prev
    Next
    INDEX
    Explanations

    the pattern 'qu' followed by either a word or another letter

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "qu"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HAEL
    -0.91
    hyde
    -0.72
    AGES
    -0.72
    ocene
    -0.70
    OLOGY
    -0.66
    zsche
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.66
    WARE
    -0.66
    nown
    -0.65
    ãĤ¹ãĥĪ
    -0.65
    POSITIVE LOGITS
    idd
    1.05
    itted
    0.94
    ipped
    0.92
    icks
    0.91
    inoa
    0.90
    aciously
    0.89
    ipp
    0.89
    arre
    0.88
    aqu
    0.87
    ishable
    0.86
    Activations Density 0.011%

    No Known Activations