© 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. 18343
    Prev
    Next
    INDEX
    Explanations

    mentions of durations of time, such as "a couple of years" or "a few weeks"

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" appearing multiple times throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases describing a duration of time and containing the words "for a"

    Explanation Uploaded by User
    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
    Att
    -0.72
    peed
    -0.68
    adin
    -0.67
    Contents
    -0.65
    Enjoy
    -0.64
    marks
    -0.64
    oids
    -0.64
    Links
    -0.63
    Cho
    -0.62
    rules
    -0.62
    POSITIVE LOGITS
     sake
    1.04
     multitude
    0.97
     variety
    0.94
     couple
    0.92
     bunch
    0.92
     foreseeable
    0.90
     few
    0.89
     reason
    0.89
     handful
    0.87
     whopping
    0.85
    Activations Density 0.131%

    No Known Activations