© 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. 8-RES-JB
    11. 23886
    Prev
    Next
    INDEX
    Explanations

    specific instances or examples being highlighted or referenced

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or attributions made by individuals or groups

    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
    soever
    -0.89
    mare
    -0.88
    mask
    -0.82
    spawn
    -0.80
    iott
    -0.76
    emy
    -0.73
    depth
    -0.70
    mire
    -0.70
    terness
    -0.70
    bit
    -0.69
    POSITIVE LOGITS
     similarities
    0.89
     successes
    0.76
     anecdotal
    0.75
     examples
    0.71
     positives
    0.71
     inconsistencies
    0.70
     another
    0.69
     literature
    0.68
     weaknesses
    0.67
     areas
    0.66
    Activations Density 0.095%

    No Known Activations