© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22423
    Prev
    Next
    INDEX
    Explanations

    specific mentions of a character named "Aq" with varying degrees of specificity

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with names containing "aq" or similar patterns

    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
     Opera
    -0.65
     won
    -0.65
    pling
    -0.64
     baked
    -0.62
     creators
    -0.61
     Valent
    -0.61
     chocolate
    -0.60
     creator
    -0.60
     benef
    -0.59
     riders
    -0.58
    POSITIVE LOGITS
    aq
    4.90
    aqu
    1.96
    iq
    1.48
    aan
    1.41
    eq
    1.21
    aah
    1.18
    aque
    1.11
    q
    1.09
    oof
    1.06
    raq
    1.05
    Activations Density 0.010%

    No Known Activations