© 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. 436
    Prev
    Next
    INDEX
    Explanations

    references to magical elements or events

    oai_token-act-pair · gpt-3.5-turbo

    references to magical themes and elements

    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
    iers
    -0.78
    cham
    -0.76
    rained
    -0.76
     Strauss
    -0.70
    avis
    -0.70
    bsp
    -0.66
    umers
    -0.66
    apers
    -0.65
    Sharp
    -0.65
    consumer
    -0.64
    POSITIVE LOGITS
    ity
    0.86
     significance
    0.78
     Haram
    0.77
    NESS
    0.76
     beasts
    0.74
    ness
    0.73
    ty
    0.72
     Voy
    0.70
    ãĥ³
    0.69
     aspects
    0.68
    Activations Density 0.041%

    No Known Activations