© 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. 10-RES-JB
    11. 10154
    Prev
    Next
    INDEX
    Explanations

    suggestions or recommendations based on a given context

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating safety or reasonableness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reborn
    -0.69
     Bridges
    -0.67
     Tonight
    -0.66
    natureconservancy
    -0.66
     Integrity
    -0.61
     Plenty
    -0.61
     SX
    -0.61
    oken
    -0.61
     Gazette
    -0.60
     VIDEOS
    -0.60
    POSITIVE LOGITS
     assume
    1.68
     presume
    1.59
     conclude
    1.56
     speculate
    1.52
     infer
    1.47
     hypothes
    1.38
     believe
    1.37
     accuse
    1.36
     argue
    1.33
     say
    1.31
    Activations Density 0.274%

    No Known Activations