© 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. 7-RES-JB
    11. 12467
    Prev
    Next
    INDEX
    Explanations

    words related to business, technology, and educational settings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of media, personal identification, and their representation within different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahu
    -0.66
    izon
    -0.64
    uckland
    -0.61
    otin
    -0.61
     suspic
    -0.60
    pload
    -0.59
    cus
    -0.59
    pard
    -0.58
     Staten
    -0.57
    erning
    -0.57
    POSITIVE LOGITS
     alike
    1.02
    ãĤ©
    0.89
     combo
    0.84
     thereof
    0.82
     respectively
    0.78
     versa
    0.77
     habits
    0.75
     thereto
    0.73
     preferences
    0.73
     holdings
    0.71
    Activations Density 0.326%

    No Known Activations