© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4114
    Prev
    Next
    INDEX
    Explanations

    mentions of items related to a specific theme or subject, which seems to be related to some form of brand or product called "Che"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific products, brands, or celebrity names associated with pop culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    Premium
    -0.59
    ufact
    -0.58
    SPONSORED
    -0.58
    imester
    -0.58
    vp
    -0.56
     DRAG
    -0.56
     srfAttach
    -0.56
     assistants
    -0.55
     foremost
    -0.55
    gage
    -0.53
    POSITIVE LOGITS
    velt
    0.79
    amia
    0.78
    atra
    0.75
    estone
    0.74
     Sheet
    0.71
    ebook
    0.71
    erella
    0.71
     Chong
    0.70
    é¾
    0.70
    ecake
    0.69
    Activations Density 0.101%

    No Known Activations