© 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. 6527
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "were" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "were" 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
    oire
    -0.70
    lag
    -0.69
    iates
    -0.68
    izes
    -0.66
    leck
    -0.65
    mare
    -0.64
    iator
    -0.64
    esian
    -0.63
    ling
    -0.62
    ledge
    -0.61
    POSITIVE LOGITS
    wolves
    1.56
    wolf
    1.14
     able
    1.03
     unable
    0.96
     subjected
    0.93
     originally
    0.89
     supposed
    0.88
     instrumental
    0.88
    senal
    0.86
     initially
    0.85
    Activations Density 0.224%

    No Known Activations