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. 9748
    Prev
    Next
    INDEX
    Explanations

    phrases indicating it is too early to make a definitive statement or prediction

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to timings and early phases of events

    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
    onyms
    -0.68
    discrimination
    -0.63
     LIFE
    -0.61
     quint
    -0.60
    verbs
    -0.58
     bil
    -0.57
    lift
    -0.56
    ractor
    -0.56
    Tur
    -0.56
     doubles
    -0.56
    POSITIVE LOGITS
    ittal
    0.84
     infancy
    0.84
     TBD
    0.71
     provisional
    0.69
     Preview
    0.67
     nascent
    0.66
    Draft
    0.66
     gestation
    0.65
     yet
    0.64
     preview
    0.64
    Activations Density 0.197%

    No Known Activations