© 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. 1454
    Prev
    Next
    INDEX
    Explanations

    technical terms or concepts underlying a topic or subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the term "underlying."

    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
    cellence
    -0.77
    alde
    -0.77
    asia
    -0.76
    ooters
    -0.74
    ander
    -0.72
    zanne
    -0.71
    chin
    -0.71
    cture
    -0.70
    efully
    -0.69
    zzi
    -0.68
    POSITIVE LOGITS
     underlying
    0.88
    Versions
    0.76
    SourceFile
    0.75
     themes
    0.72
     motivations
    0.72
    verse
    0.70
     layers
    0.70
     underpin
    0.69
    layer
    0.69
     theme
    0.67
    Activations Density 0.011%

    No Known Activations