© 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. 361
    Prev
    Next
    INDEX
    Explanations

    expressions related to a small part representing a larger whole or a significant issue

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something significant or foundational beneath the surface

    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
    Merit
    -0.93
    FACE
    -0.78
    MF
    -0.71
    ials
    -0.71
    ailability
    -0.71
    Priv
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
    Ü
    -0.69
    ouver
    -0.68
    EMENT
    -0.67
    POSITIVE LOGITS
     iceberg
    1.17
    acle
    0.84
    yip
    0.75
     toes
    0.71
     Rai
    0.71
    ariat
    0.70
     tails
    0.70
    ulum
    0.69
     scales
    0.67
     Racer
    0.66
    Activations Density 0.087%

    No Known Activations