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. 12-RES-JB
    6. 6929
    Prev
    Next
    INDEX
    Explanations

    interjections expressing surprise or excitement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions of amazement or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riot
    -0.73
    mus
    -0.71
    mun
    -0.68
    pod
    -0.67
     Anthem
    -0.66
     Mend
    -0.66
    tic
    -0.64
    matic
    -0.63
    bre
    -0.63
    nic
    -0.61
    POSITIVE LOGITS
    efully
    1.03
    OOOO
    1.00
    aah
    0.98
    HHHH
    0.96
    OO
    0.92
    OOOOOOOO
    0.90
    osh
    0.90
    olly
    0.90
    ooky
    0.89
    ogie
    0.89
    Activations Density 0.140%

    No Known Activations