© 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. 7-RES-JB
    11. 17939
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate variance or dependency on different conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating dependency or variation based on certain conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥį
    -0.87
    ģ«
    -0.77
    lyn
    -0.77
    İĭ
    -0.77
    ļéĨĴ
    -0.74
    roo
    -0.72
    umerable
    -0.70
    ãĥ¯
    -0.69
    without
    -0.69
    ogenesis
    -0.67
    POSITIVE LOGITS
     severity
    0.93
     circumstance
    0.73
     circumstances
    0.71
     actionGroup
    0.70
     outcome
    0.68
     specialization
    0.66
     disposition
    0.66
     seriousness
    0.65
     occasion
    0.65
     Unic
    0.64
    Activations Density 0.137%

    No Known Activations