© 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. 11-RES-JB
    11. 1746
    Prev
    Next
    INDEX
    Explanations

    potential actions or decisions related to individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to political and legal issues

    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
     ILCS
    -0.77
    handle
    -0.65
    `.
    -0.62
    cknow
    -0.62
     avg
    -0.61
    ichen
    -0.60
    %.
    -0.58
    Fra
    -0.58
    Ô
    -0.56
    sit
    -0.53
    POSITIVE LOGITS
     surfaced
    1.27
     coincided
    1.27
     stems
    1.26
     stemmed
    1.26
     coincides
    1.21
     persisted
    1.21
     emerged
    1.19
     hinges
    1.19
     arose
    1.18
     prompted
    1.16
    Activations Density 0.454%

    No Known Activations