© 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. 10615
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual or imaginative experiences

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional or dramatic expressions related to social issues

    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
     dispers
    -0.75
     bonded
    -0.71
     scatter
    -0.71
     scattering
    -0.71
     detached
    -0.70
     barrier
    -0.70
     floating
    -0.67
     shroud
    -0.67
     Bermuda
    -0.66
     confinement
    -0.66
    POSITIVE LOGITS
    ¹
    1.07
    į
    1.00
    Į
    0.99
    £
    0.98
    ¤
    0.95
    ĸļ
    0.94
    º
    0.93
    ¡
    0.93
    Ķ
    0.91
    Ĭ
    0.91
    Activations Density 0.161%

    No Known Activations