© 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. 23350
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives that indicate a significant or sudden change or increase

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sharply" in relation to changes or comparisons

    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
    itu
    -0.82
    gres
    -0.79
    ota
    -0.76
    ession
    -0.74
    rity
    -0.74
    OTA
    -0.71
    sites
    -0.71
    orno
    -0.71
    oa
    -0.69
    lymp
    -0.67
    POSITIVE LOGITS
     sharply
    0.97
     diver
    0.80
     leveled
    0.78
     downwards
    0.77
     divergence
    0.71
     deline
    0.70
     conclud
    0.70
     downward
    0.69
     distingu
    0.69
     shifts
    0.68
    Activations Density 0.004%

    No Known Activations