© 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. 7660
    Prev
    Next
    INDEX
    Explanations

    words related to political and social issues

    oai_token-act-pair · gpt-3.5-turbo

    references to various political and social issues

    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
    ramids
    -0.85
    onz
    -0.75
    ardi
    -0.72
    DOS
    -0.72
    ardo
    -0.71
    alg
    -0.71
    amaz
    -0.70
     Thumbnails
    -0.70
     Bom
    -0.69
    raid
    -0.68
    POSITIVE LOGITS
     pertaining
    1.19
     relating
    1.09
     affecting
    1.04
     imaginable
    0.98
     related
    0.95
     matters
    0.93
     involving
    0.92
    matter
    0.89
     ranging
    0.89
     impacting
    0.87
    Activations Density 0.165%

    No Known Activations