© 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. 6-RES-JB
    11. 4476
    Prev
    Next
    INDEX
    Explanations

    phrases related to pointing out or emphasizing things

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recognizes
    -0.77
     allows
    -0.76
     owes
    -0.75
     gives
    -0.71
     exceeds
    -0.71
     could
    -0.71
     provides
    -0.71
     doesn
    -0.71
     enables
    -0.70
    mares
    -0.70
    POSITIVE LOGITS
     smallest
    0.96
     usual
    0.96
     difference
    0.96
     same
    0.95
     biggest
    0.93
     longest
    0.93
     earliest
    0.92
     latest
    0.92
     simplest
    0.92
     fastest
    0.91
    Activations Density 0.211%

    No Known Activations