© 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. 22524
    Prev
    Next
    INDEX
    Explanations

    the word "initially" in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "initially" 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
    =-=-=-=-=-=-=-=-
    -0.69
     Diseases
    -0.68
    rf
    -0.68
    helm
    -0.68
    gre
    -0.68
     Chef
    -0.67
     Gloves
    -0.67
    nce
    -0.67
    knife
    -0.66
    rom
    -0.66
    POSITIVE LOGITS
     responders
    0.88
     blush
    0.85
     hes
    0.82
     hesitant
    0.80
     conceived
    0.80
     hesitated
    0.79
     unsuccessfully
    0.79
     attracted
    0.79
     appeared
    0.78
     doubted
    0.77
    Activations Density 0.029%

    No Known Activations