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. 9732
    Prev
    Next
    INDEX
    Explanations

    phrases indicating location or direction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "one of" indicating examples or categories

    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
    lees
    -0.77
    ans
    -0.70
    anse
    -0.66
    ption
    -0.65
    body
    -0.65
    etermination
    -0.64
    matter
    -0.62
     disadvant
    -0.60
    leans
    -0.60
    ening
    -0.59
    POSITIVE LOGITS
     these
    0.77
     Europe
    0.76
     those
    0.75
     three
    0.75
     our
    0.74
     Britain
    0.74
     two
    0.72
     America
    0.72
     my
    0.71
     innumerable
    0.70
    Activations Density 0.071%

    No Known Activations