© 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. 23721
    Prev
    Next
    INDEX
    Explanations

    directives or instructions prompting actions

    oai_token-act-pair · gpt-3.5-turbo

    commands or suggestions for action

    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
    ģĸ
    -0.77
    alf
    -0.72
    Impl
    -0.72
    ĨĴ
    -0.69
    onel
    -0.67
    ELD
    -0.66
    ļé
    -0.64
    ãĤ¦ãĤ¹
    -0.61
     millenn
    -0.61
     impossibility
    -0.61
    POSITIVE LOGITS
     mention
    1.11
     check
    1.05
     bookmark
    0.99
     include
    0.94
     specify
    0.89
     nominate
    0.86
     Include
    0.84
     checkout
    0.83
     ask
    0.81
     rinse
    0.79
    Activations Density 0.085%

    No Known Activations