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. 582
    Prev
    Next
    INDEX
    Explanations

    phrases related to things happening at the current moment or recent past

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases indicating a change or transition in situation or perspective

    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
    aro
    -0.71
    æ©
    -0.69
    ocaust
    -0.68
    oeuv
    -0.67
    uty
    -0.66
    pill
    -0.65
    assadors
    -0.64
    WAYS
    -0.63
    iege
    -0.63
    duty
    -0.63
    POSITIVE LOGITS
    rely
    0.74
     we
    0.72
     pesky
    0.70
     wraps
    0.67
    adays
    0.66
     settles
    0.64
    ched
    0.62
    stock
    0.61
     sounds
    0.60
    veyard
    0.58
    Activations Density 0.045%

    No Known Activations