© 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. 0-RES-JB
    6. 6772
    Prev
    Next
    INDEX
    Explanations

    words related to different types of meats

    oai_token-act-pair · gpt-3.5-turbo

    mentions of meat in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Offline
    -0.91
    Atl
    -0.71
    Desk
    -0.70
     Princ
    -0.69
     Bubble
    -0.68
    Storm
    -0.68
    Republic
    -0.67
    Catal
    -0.66
     Grad
    -0.65
    aunder
    -0.65
    POSITIVE LOGITS
     meat
    3.42
    meat
    2.83
    Meat
    2.69
     Meat
    2.66
     meats
    2.57
     beef
    1.96
     pork
    1.94
     steak
    1.87
     Beef
    1.82
     sausage
    1.69
    Activations Density 0.027%

    No Known Activations