© 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. 0-RES-JB
    11. 2914
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to question and answer formats

    oai_token-act-pair · gpt-3.5-turbo

    references to the letter "Q"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anish
    -0.77
    Dispatch
    -0.70
    angered
    -0.65
    nown
    -0.65
    kins
    -0.64
    enos
    -0.63
    ldom
    -0.62
    orious
    -0.60
     enshr
    -0.60
    abet
    -0.59
    POSITIVE LOGITS
     Q
    3.64
    Q
    2.54
     q
    2.04
     Qt
    1.72
     QR
    1.62
    q
    1.59
     QC
    1.46
    qt
    1.41
     AQ
    1.39
    QL
    1.37
    Activations Density 0.018%

    No Known Activations