© 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. 7542
    Prev
    Next
    INDEX
    Explanations

    phrases related to risks and potential negative consequences

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements related to health risks and potential consequences

    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
    urai
    -0.70
    ropolitan
    -0.63
    AH
    -0.61
     Apostles
    -0.60
     plurality
    -0.59
     Illum
    -0.58
    NES
    -0.58
    è£
    -0.57
    Nin
    -0.57
    aukee
    -0.57
    POSITIVE LOGITS
     attempting
    0.98
     untreated
    0.91
    EStreamFrame
    0.83
     accessing
    0.79
     ingest
    0.79
     inaction
    0.79
    respective
    0.77
     unprepared
    0.77
     importing
    0.76
     inability
    0.76
    Activations Density 0.552%

    No Known Activations