© 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. 492
    Prev
    Next
    INDEX
    Explanations

    Sorry, it seems I made a mistake. Let me correct that for neuron 4: Explanation of neuron 4 behavior: the main thing this neuron does is find words related to famous names or people

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    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
    ongyang
    -0.69
    rences
    -0.65
    urally
    -0.63
     plur
    -0.62
    ngth
    -0.57
    gently
    -0.56
    gencies
    -0.55
    ModLoader
    -0.55
     nationally
    -0.55
     regrett
    -0.54
    POSITIVE LOGITS
    igans
    1.51
    ovic
    1.39
    ova
    1.39
    ovich
    1.37
    ov
    1.32
    ese
    1.25
    omics
    1.22
    athan
    1.21
    owski
    1.17
    igan
    1.16
    Activations Density 0.198%

    No Known Activations