© 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. 17372
    Prev
    Next
    INDEX
    Explanations

    terms related to the field of arts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the arts

    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
     Adin
    -0.76
    odder
    -0.73
    aded
    -0.68
    ading
    -0.67
    zee
    -0.66
     Paragu
    -0.66
    utations
    -0.66
    utable
    -0.66
    utation
    -0.65
    agher
    -0.64
    POSITIVE LOGITS
    manship
    1.14
    esian
    1.05
     arts
    0.93
    cape
    0.91
    chool
    0.83
    pace
    0.82
    isans
    0.82
     Arts
    0.80
    alon
    0.78
    Craft
    0.78
    Activations Density 0.026%

    No Known Activations