© 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. 4-RES-JB
    11. 693
    Prev
    Next
    INDEX
    Explanations

    references to legal actions and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to financial investments and vested interests

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

    No Comments

    Negative Logits
    xus
    -0.72
    ught
    -0.68
    uddin
    -0.67
    uador
    -0.66
    cius
    -0.66
    Phil
    -0.66
    Downloadha
    -0.66
    sterdam
    -0.64
     unprepared
    -0.64
    gettable
    -0.64
    POSITIVE LOGITS
    eering
    0.85
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.84
    ress
    0.83
    vest
    0.81
    als
    0.74
    itious
    0.74
    ãĥ¼ãĥĨãĤ£
    0.73
    sylvania
    0.72
    eria
    0.72
    alling
    0.71
    Activations Density 0.011%

    No Known Activations