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. 4-RES-JB
    6. 5939
    Prev
    Next
    INDEX
    Explanations

    verbs or actions related to strong and often drastic actions or decisions

    oai_token-act-pair · gpt-3.5-turbo

    action verbs indicating significant activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    been
    -0.59
    yond
    -0.53
    copy
    -0.52
    emate
    -0.51
    estate
    -0.49
    estone
    -0.47
    arb
    -0.47
    é¾įåĸļ士
    -0.46
    orest
    -0.46
    arsity
    -0.46
    POSITIVE LOGITS
     yesterday
    0.52
     BART
    0.50
     showc
    0.50
     tremend
    0.49
     him
    0.47
     harshly
    0.46
    hes
    0.46
    nces
    0.45
     abruptly
    0.45
     briefly
    0.45
    Activations Density 0.756%

    No Known Activations