© 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. 9-RES-JB
    11. 18553
    Prev
    Next
    INDEX
    Explanations

    exact matches of specific words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing precision or clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extensively
    -0.71
     vigorously
    -0.69
    asta
    -0.67
     enthusiastically
    -0.67
    rift
    -0.67
    strong
    -0.66
     greatly
    -0.64
     enormously
    -0.63
     Flavoring
    -0.62
    ker
    -0.61
    POSITIVE LOGITS
     opposite
    0.89
    ãĤ¨
    0.77
    ifiable
    0.70
     zero
    0.66
    itude
    0.65
    inct
    0.65
    paste
    0.64
    çĶ°
    0.64
    rex
    0.63
     analogous
    0.63
    Activations Density 0.027%

    No Known Activations