© 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. 9-RES-JB
    11. 15497
    Prev
    Next
    INDEX
    Explanations

    terms related to safety

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eric
    -0.96
    issance
    -0.90
    yss
    -0.86
    naire
    -0.83
    erers
    -0.78
    erer
    -0.77
    nant
    -0.75
    nai
    -0.75
    estine
    -0.74
    fred
    -0.74
    POSITIVE LOGITS
     precautions
    0.98
     hazards
    0.96
     net
    0.92
     hazard
    0.91
     valve
    0.89
     nets
    0.87
     valves
    0.83
     precaution
    0.83
     margins
    0.79
     margin
    0.76
    Activations Density 0.045%

    No Known Activations