© 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. 11-RES-JB
    11. 15683
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a deep understanding or serious consideration of a concept or idea

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "taken" 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
    eers
    -0.64
     reinforcement
    -0.63
     Zucker
    -0.62
    glers
    -0.59
     SPD
    -0.58
     icing
    -0.58
    Split
    -0.57
    FTWARE
    -0.57
    ileaks
    -0.57
     Machina
    -0.56
    POSITIVE LOGITS
     aback
    1.56
     advantage
    1.21
     care
    1.14
     seriously
    1.08
     hostage
    1.05
     orally
    0.94
     Seriously
    0.90
     apart
    0.90
    care
    0.85
    aways
    0.84
    Activations Density 0.039%

    No Known Activations