© 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. 6-RES-JB
    11. 10771
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal attributes or traits

    oai_token-act-pair · gpt-3.5-turbo

    connective phrases and discourse markers indicating relationships and conditions in sentences

    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
     spur
    -0.74
    ussions
    -0.71
    ullivan
    -0.70
    ioxide
    -0.69
    ISION
    -0.68
    USS
    -0.67
    ãĥ¯ãĥ³
    -0.66
    izens
    -0.65
    isions
    -0.65
    rils
    -0.63
    POSITIVE LOGITS
    albeit
    0.77
     albeit
    0.76
     discipl
    0.73
     specializing
    0.72
     persecuted
    0.70
     although
    0.69
     Sly
    0.68
     liar
    0.68
     pretending
    0.67
     educator
    0.66
    Activations Density 0.491%

    No Known Activations