© 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. 0-RES-JB
    11. 2854
    Prev
    Next
    INDEX
    Explanations

    commands or instructions, particularly those involving code

    oai_token-act-pair · gpt-3.5-turbo

    commands involving the term "set."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     finger
    -0.60
     fault
    -0.58
     fruit
    -0.58
     colleges
    -0.57
     misses
    -0.57
     handic
    -0.57
     knees
    -0.57
     prisons
    -0.57
     kidding
    -0.57
     doctors
    -0.56
    POSITIVE LOGITS
    set
    4.14
    sets
    2.83
    SET
    2.10
    Set
    2.06
    setting
    2.03
     set
    1.81
     Set
    1.79
     sets
    1.50
     Sets
    1.30
     SET
    1.27
    Activations Density 0.008%

    No Known Activations