© 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. 18706
    Prev
    Next
    INDEX
    Explanations

    phrases related to being operational or in working conditions

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that connect phrases or ideas

    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
    pmwiki
    -0.86
    ãĤ´ãĥ³
    -0.72
    ast
    -0.68
    ylon
    -0.68
    uel
    -0.68
    uyomi
    -0.66
    regate
    -0.66
    ulkan
    -0.65
    stice
    -0.65
    ruce
    -0.65
    POSITIVE LOGITS
     ready
    1.51
     awaiting
    1.20
     waiting
    1.14
     alive
    1.10
     poised
    1.08
     willing
    1.06
     primed
    1.04
     functioning
    1.04
     behaving
    1.03
    ready
    1.01
    Activations Density 0.187%

    No Known Activations