© 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. 4-RES-JB
    11. 12396
    Prev
    Next
    INDEX
    Explanations

    adjectives related to intelligence or creativity

    oai_token-act-pair · gpt-3.5-turbo

    concepts associated with cleverness and creativity

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

    No Comments

    Negative Logits
    ACP
    -0.67
    asta
    -0.65
    enf
    -0.61
    avored
    -0.61
    thood
    -0.61
    ocal
    -0.61
     witnessed
    -0.60
    Af
    -0.59
    ittee
    -0.59
    astered
    -0.58
    POSITIVE LOGITS
    ly
    1.24
    nesses
    0.97
    glers
    0.85
     enough
    0.81
     tricks
    0.79
     twist
    0.77
     twists
    0.74
     clever
    0.73
    sonian
    0.73
    fully
    0.72
    Activations Density 0.019%

    No Known Activations