© 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. 3065
    Prev
    Next
    INDEX
    Explanations

    phrases related to the verb "say" followed by other words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Say" in various 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
    ¥ŀ
    -0.73
    ifact
    -0.71
    abwe
    -0.70
    xtap
    -0.68
    iscopal
    -0.67
    ocaust
    -0.64
     fullest
    -0.63
    ciating
    -0.63
    ician
    -0.62
    ombs
    -0.62
    POSITIVE LOGITS
     goodbye
    1.17
     hello
    0.98
    enger
    0.90
    eed
    0.87
    ings
    0.86
     aloud
    0.83
    arin
    0.83
    aka
    0.76
    y
    0.75
    nard
    0.74
    Activations Density 0.044%

    No Known Activations