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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9326
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or change

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "also" and related quantifying adverbs

    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
    yond
    -0.66
    etting
    -0.65
    Subject
    -0.63
    YING
    -0.60
    GROUND
    -0.56
    aq
    -0.56
    idding
    -0.55
    Rap
    -0.55
     Digest
    -0.55
     Carm
    -0.54
    POSITIVE LOGITS
    been
    1.60
     been
    1.50
     undergone
    1.28
     gotten
    1.19
     Been
    1.11
     become
    1.10
     begun
    1.09
     fallen
    1.08
     gone
    1.04
     come
    1.00
    Activations Density 0.154%

    No Known Activations