© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7916
    Prev
    Next
    INDEX
    Explanations

    words related to philosophical or belief systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various "istic" descriptors, indicating abstract concepts or styles

    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
    lain
    -1.03
    clips
    -0.90
    BOOK
    -0.82
    leaf
    -0.80
    FACE
    -0.77
    wright
    -0.76
    ãģ®éŃĶ
    -0.74
    ortium
    -0.72
    yard
    -0.72
    handle
    -0.72
    POSITIVE LOGITS
     tendencies
    0.95
     imperative
    0.74
     endeavors
    0.74
     persuasion
    0.73
     fallacy
    0.73
     motives
    0.73
     conversion
    0.70
     asylum
    0.70
    ated
    0.70
    orical
    0.69
    Activations Density 0.029%

    No Known Activations