© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 7787
    Prev
    Next
    INDEX
    Explanations

    references to plans and proposals

    oai_token-act-pair · gpt-3.5-turbo

    references to planned actions or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Appearance
    -0.77
    xtap
    -0.65
    çīĪ
    -0.63
     VIDEOS
    -0.60
    ETHOD
    -0.60
     somet
    -0.60
    shapeshifter
    -0.59
    ãĤ©
    -0.59
     humble
    -0.58
    Ô
    -0.58
    POSITIVE LOGITS
     altogether
    1.28
     indefinitely
    0.91
     entirely
    0.91
    essential
    0.85
     prematurely
    0.83
     relating
    0.76
     favoring
    0.75
     aimed
    0.75
     Blumenthal
    0.74
     unnecessarily
    0.74
    Activations Density 0.320%

    No Known Activations