© 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. 1-RES-JB
    11. 24138
    Prev
    Next
    INDEX
    Explanations

    phrases related to fulfilling obligations or requirements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "meet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trop
    -0.91
    cffffcc
    -0.85
    etheless
    -0.85
    culus
    -0.81
    obe
    -0.79
     srf
    -0.74
    uyomi
    -0.73
    ¥ŀ
    -0.73
    cul
    -0.72
    secut
    -0.72
    POSITIVE LOGITS
     Meet
    0.94
     meet
    0.90
    enance
    0.85
    ings
    0.83
     meets
    0.82
    aunt
    0.79
    INGS
    0.78
    ingly
    0.77
     met
    0.76
     Dame
    0.76
    Activations Density 0.020%

    No Known Activations