© 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. 10247
    Prev
    Next
    INDEX
    Explanations

    terms related to technical aspects such as modules, plugins, and support

    oai_token-act-pair · gpt-3.5-turbo

    references to propulsion or motivation in a broader context

    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
     Eston
    -0.86
    ê
    -0.81
     Titanic
    -0.81
    keyes
    -0.80
     Fitzgerald
    -0.80
     Assy
    -0.79
    Haw
    -0.79
    Bird
    -0.79
     Tammy
    -0.79
     Harden
    -0.78
    POSITIVE LOGITS
     Mod
    2.14
     MOD
    1.91
    Mod
    1.89
     mod
    1.83
    mod
    1.82
    MOD
    1.81
     Mods
    1.64
     mods
    1.55
    mods
    1.46
     modules
    1.42
    Activations Density 0.265%

    No Known Activations