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. 9-RES-JB
    6. 909
    Prev
    Next
    INDEX
    Explanations

    the word "pizza" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Mozzarella"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spect
    -0.68
     Polar
    -0.66
     compl
    -0.66
    warming
    -0.60
     Span
    -0.60
     conspicuous
    -0.59
     Patriot
    -0.59
    ©¶æ
    -0.59
     entitle
    -0.58
     Malays
    -0.58
    POSITIVE LOGITS
    arella
    1.37
    etta
    1.10
    arro
    1.09
    azz
    1.07
    erella
    1.03
    ombies
    0.98
    hou
    0.95
    eria
    0.95
    ucc
    0.94
    zz
    0.93
    Activations Density 0.052%

    No Known Activations