© 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. 8-RES-JB
    11. 20223
    Prev
    Next
    INDEX
    Explanations

    instances of the word "let" followed by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "let" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cumbers
    -0.94
    DAY
    -0.70
    ILY
    -0.69
     resil
    -0.69
    ecause
    -0.68
    liest
    -0.67
    manship
    -0.66
    ULTS
    -0.65
    PLIED
    -0.64
    rown
    -0.64
    POSITIVE LOGITS
    tered
    1.09
    ting
    0.97
    ariat
    0.95
    oad
    0.95
    arget
    0.89
    rack
    0.88
    own
    0.88
    ocol
    0.87
    arius
    0.84
    tering
    0.83
    Activations Density 0.028%

    No Known Activations