© 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. 6-RES-JB
    11. 11703
    Prev
    Next
    INDEX
    Explanations

    phrases related to the justice system and medical conditions impacting the body

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of systems, specifically focusing on justice and immune systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ±
    -0.74
    brew
    -0.73
    ajor
    -0.72
    sbm
    -0.72
    ãĤ¤ãĥĪ
    -0.69
     Lantern
    -0.68
    Sund
    -0.68
    vari
    -0.68
    20439
    -0.67
    tein
    -0.67
    POSITIVE LOGITS
    atics
    0.88
     Anthem
    0.77
     sclerosis
    0.73
     purse
    0.68
     modernization
    0.68
     bureaucracy
    0.68
     traged
    0.66
     dysfunction
    0.66
    ĸļ
    0.66
     deregulation
    0.66
    Activations Density 0.179%

    No Known Activations