© 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. 18676
    Prev
    Next
    INDEX
    Explanations

    phrases describing contrasts or differences between entities or conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and" indicating conjunctions or connections between different ideas or concepts

    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
     Citation
    -0.78
    Voice
    -0.71
    @#&
    -0.71
    elle
    -0.70
    hei
    -0.70
    Dri
    -0.69
    iard
    -0.69
    ãĤ¨
    -0.68
    yn
    -0.68
    )</
    -0.68
    POSITIVE LOGITS
     ours
    0.96
     those
    0.80
     actual
    0.79
     theirs
    0.76
     hence
    0.72
     yours
    0.72
     downright
    0.70
     ones
    0.67
     customary
    0.67
     reality
    0.66
    Activations Density 0.131%

    No Known Activations