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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15118
    Prev
    Next
    INDEX
    Explanations

    mentions of sudden changes or shifts

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or patterns starting with "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ATURES
    -0.62
    sta
    -0.60
    pole
    -0.55
    mallow
    -0.55
    over
    -0.54
    tag
    -0.53
    puff
    -0.53
     Debor
    -0.53
    quickShipAvailable
    -0.53
     allowance
    -0.53
    POSITIVE LOGITS
     sudden
    1.11
     lifetime
    0.82
     magnitude
    0.74
     kind
    0.74
    ught
    0.70
    ugh
    0.70
    venture
    0.70
     thousand
    0.69
     century
    0.69
     Lifetime
    0.67
    Activations Density 0.066%

    No Known Activations