© 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. 1-RES-JB
    11. 3491
    Prev
    Next
    INDEX
    Explanations

    terms related to deception or dishonesty

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to legal issues and financial activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atchewan
    -0.73
    Amazing
    -0.70
    anse
    -0.69
    ansas
    -0.66
    orpor
    -0.66
    ataka
    -0.66
    Tokens
    -0.66
     Appropri
    -0.65
     Alz
    -0.65
     Nebula
    -0.65
    POSITIVE LOGITS
     fals
    0.91
    esty
    0.88
     refin
    0.87
    inished
    0.81
    ailed
    0.78
    ibel
    0.76
    inance
    0.74
    ysis
    0.72
    ILS
    0.72
    owler
    0.71
    Activations Density 0.035%

    No Known Activations