© 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. 2-RES-JB
    11. 2038
    Prev
    Next
    INDEX
    Explanations

    user interface (UI) elements or mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to user interface (UI) elements and design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.87
    inosaur
    -0.77
    wagen
    -0.72
    aunder
    -0.69
    ership
    -0.68
    itional
    -0.68
    given
    -0.65
    bring
    -0.65
    ãĤ·ãĥ£
    -0.64
    actory
    -0.64
    POSITIVE LOGITS
    UI
    1.16
    PDATE
    0.94
     UI
    0.87
    BG
    0.84
    UC
    0.80
    selage
    0.79
    ULTS
    0.78
    FFER
    0.75
     hoops
    0.74
    UX
    0.74
    Activations Density 0.007%

    No Known Activations