© 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. 18768
    Prev
    Next
    INDEX
    Explanations

    mentions of hypothetical scenarios/actions not taken

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions or impacts

    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
    rawdownloadcloneembedreportprint
    -0.74
    ilial
    -0.66
    */(
    -0.65
     externalToEVAOnly
    -0.63
     progresses
    -0.58
    atten
    -0.57
    FY
    -0.56
     extends
    -0.56
     underside
    -0.56
    sup
    -0.55
    POSITIVE LOGITS
    would
    1.27
     wouldn
    1.23
     would
    1.13
     Would
    1.12
    'd
    1.04
     Wouldn
    1.00
    Would
    0.99
     probably
    0.94
    probably
    0.90
     surely
    0.89
    Activations Density 0.276%

    No Known Activations