© 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. 8-RES-JB
    11. 6431
    Prev
    Next
    INDEX
    Explanations

    words related to actions that involve guidance, control, and manipulation

    oai_token-act-pair · gpt-3.5-turbo

    references to processes, actions, or states pertaining to focus and clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.74
     Sunshine
    -0.70
     resemblance
    -0.67
     Kaiser
    -0.65
     elementary
    -0.62
     Eden
    -0.61
    DragonMagazine
    -0.61
    ibrary
    -0.61
    renheit
    -0.61
    ãĤ·ãĥ£
    -0.59
    POSITIVE LOGITS
    wrote
    0.94
    ifies
    0.90
    ulates
    0.88
    izes
    0.87
     versa
    0.83
    posing
    0.81
    poses
    0.80
    ify
    0.79
    orting
    0.76
    icing
    0.76
    Activations Density 0.307%

    No Known Activations