© 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. 7-RES-JB
    11. 16724
    Prev
    Next
    INDEX
    Explanations

    differences between past and present situations or arrangements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "previously" indicating past occurrences or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.93
    ioxide
    -0.71
    ãĤ¢ãĥ«
    -0.71
    ãĥ¥
    -0.71
    alias
    -0.69
    Rust
    -0.67
    Requirements
    -0.66
    olves
    -0.64
    lez
    -0.64
    inates
    -0.64
    POSITIVE LOGITS
     however
    0.83
     there
    0.76
     though
    0.70
    there
    0.65
     campaigners
    0.62
     pled
    0.61
     Indians
    0.61
    had
    0.60
     opponents
    0.60
     Britons
    0.60
    Activations Density 0.148%

    No Known Activations