Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 8762
    Prev
    Next
    INDEX
    Explanations

    biographical information and events in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "had been" indicating ongoing or past actions and experiences

    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
    iverse
    -0.72
    cious
    -0.72
     anymore
    -0.62
     VIDEOS
    -0.61
     taxp
    -0.60
     2018
    -0.59
     OLED
    -0.59
     partName
    -0.59
    uesday
    -0.58
     Mov
    -0.58
    POSITIVE LOGITS
     previously
    1.02
     earlier
    0.93
     exha
    0.88
     looph
    0.83
     previous
    0.81
     hitherto
    0.73
     beforehand
    0.72
     hoped
    0.70
     planned
    0.69
     intending
    0.68
    Activations Density 0.285%

    No Known Activations