© 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. 13546
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "said" alongside a description of accompanying actions or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of quoted speech or statements made by individuals

    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
    Pont
    -0.79
    peror
    -0.75
    ãĥİ
    -0.73
    EEE
    -0.72
    éĹĺ
    -0.72
    士
    -0.71
    lite
    -0.71
    Runtime
    -0.70
    ãĥ¯
    -0.70
    âĨ
    -0.69
    POSITIVE LOGITS
     goodbye
    1.06
     hello
    0.89
     neighbour
    0.79
     neighbours
    0.78
     afterward
    0.78
     neighbor
    0.77
     aloud
    0.72
     neighbors
    0.71
     afterwards
    0.70
     plaint
    0.69
    Activations Density 0.167%

    No Known Activations