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. 10-RES-JB
    6. 10832
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to current events, such as names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    significant or critical events and situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estim
    -0.66
     flyers
    -0.64
     marg
    -0.63
    ilk
    -0.63
     iod
    -0.61
     princ
    -0.61
     printing
    -0.60
    é¾į
    -0.59
    ranch
    -0.59
    ishi
    -0.58
    POSITIVE LOGITS
     02
    1.41
     01
    1.36
     03
    1.35
     00
    1.30
     04
    1.29
     05
    1.25
     06
    1.22
     07
    1.15
     Replay
    1.13
     08
    1.13
    Activations Density 0.010%

    No Known Activations