© 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. 21252
    Prev
    Next
    INDEX
    Explanations

    phrases indicating giving or receiving something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "have."

    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
    opal
    -0.61
    dale
    -0.60
    etting
    -0.60
    女
    -0.58
    âĻ¦
    -0.57
    ELF
    -0.57
    ãĤ¼ãĤ¦ãĤ¹
    -0.57
    hack
    -0.55
    perty
    -0.54
    FTWARE
    -0.54
    POSITIVE LOGITS
     you
    1.13
     fun
    1.03
     mercy
    1.03
     patience
    0.89
     ya
    0.88
     ye
    0.87
     YOU
    0.82
     anyone
    0.81
     been
    0.79
     someone
    0.79
    Activations Density 0.038%

    No Known Activations