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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11395
    Prev
    Next
    INDEX
    Explanations

    information related to food preservation and preparation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of food and related items

    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
    renheit
    -0.67
    omaly
    -0.66
    heit
    -0.65
    irlf
    -0.63
    iov
    -0.62
    vind
    -0.61
    adobe
    -0.61
    ËĪ
    -0.61
    cus
    -0.60
     Gundam
    -0.60
    POSITIVE LOGITS
     alike
    1.80
     respectively
    1.39
     combo
    0.88
     industries
    0.87
     striped
    0.85
     interchange
    0.84
     sectors
    0.82
     separately
    0.82
     combinations
    0.79
     combination
    0.74
    Activations Density 0.413%

    No Known Activations