© 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. 7899
    Prev
    Next
    INDEX
    Explanations

    colors and physical objects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various colors, social issues, and emotional concepts

    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
    renheit
    -0.61
    antha
    -0.60
    adobe
    -0.60
    Legend
    -0.59
    Ni
    -0.59
    AAA
    -0.58
    ©¶æ
    -0.57
    isu
    -0.56
    OSP
    -0.56
    redited
    -0.55
    POSITIVE LOGITS
     alike
    2.05
     respectively
    1.76
     separately
    0.97
     interchange
    0.97
     together
    0.93
     combo
    0.91
     simultaneously
    0.87
     versa
    0.86
     etc
    0.84
     combinations
    0.84
    Activations Density 0.462%

    No Known Activations