© 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. 10-RES-JB
    11. 23281
    Prev
    Next
    INDEX
    Explanations

    phrases related to stripping or removing something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stripping, arriving, and approval/disapproval

    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
    illary
    -0.78
    icity
    -0.73
     Leilan
    -0.73
    inian
    -0.66
    icas
    -0.65
     Frey
    -0.65
     nu
    -0.63
     equity
    -0.63
     shroud
    -0.62
     board
    -0.61
    POSITIVE LOGITS
    ving
    1.76
    ves
    1.51
    pping
    1.45
    vers
    1.44
    ved
    1.42
    ppers
    1.42
    pped
    1.38
    pper
    1.37
    vable
    1.35
    ppy
    1.34
    Activations Density 0.054%

    No Known Activations