© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17021
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a process, such as cooking or crafting

    oai_token-act-pair · gpt-3.5-turbo

    instructions or methods related to food preparation and storage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ì
    -0.70
    thro
    -0.69
     senses
    -0.68
    violence
    -0.66
     governing
    -0.66
    atism
    -0.65
    involved
    -0.65
    bara
    -0.64
    cessive
    -0.63
    amacare
    -0.63
    POSITIVE LOGITS
     landfill
    0.98
     compost
    0.90
     crates
    0.85
     ILCS
    0.81
     Trash
    0.79
     museum
    0.77
     inciner
    0.77
     museums
    0.76
     scrap
    0.74
     storage
    0.73
    Activations Density 0.452%

    No Known Activations