© 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. 8-RES-JB
    11. 18582
    Prev
    Next
    INDEX
    Explanations

    actions related to physical alteration or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    actions related to hair processing and maintenance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lawy
    -0.67
    heid
    -0.66
    antics
    -0.62
    âĹ¼
    -0.62
     influencing
    -0.60
     inquest
    -0.59
    journal
    -0.58
    taboola
    -0.58
    argument
    -0.58
    PLAY
    -0.58
    POSITIVE LOGITS
     batches
    0.78
     duplicate
    0.72
     hairs
    0.72
     portions
    0.72
     entire
    0.71
     oneself
    0.70
     them
    0.70
     eggs
    0.70
     blades
    0.70
     specimens
    0.69
    Activations Density 0.372%

    No Known Activations