© 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. 11469
    Prev
    Next
    INDEX
    Explanations

    words related to physical addresses

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "addresses."

    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
    shoot
    -0.76
    ifact
    -0.68
     streak
    -0.67
    usk
    -0.64
     teammate
    -0.62
     drift
    -0.62
    loop
    -0.62
     bargain
    -0.62
    aver
    -0.61
     tendency
    -0.61
    POSITIVE LOGITS
     addresses
    3.83
     address
    1.90
     Address
    1.61
    address
    1.61
    Address
    1.55
     addressed
    1.39
     URLs
    1.39
     addressing
    1.38
     handles
    1.36
     aliases
    1.36
    Activations Density 0.016%

    No Known Activations