© 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. 10-RES-JB
    11. 10228
    Prev
    Next
    INDEX
    Explanations

    words related to the judicial/criminal process and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cipled
    -0.68
     Opportun
    -0.63
    itech
    -0.62
    apego
    -0.61
    recated
    -0.61
    itialized
    -0.60
    ahoo
    -0.59
    partisan
    -0.58
    ookie
    -0.57
    é£
    -0.57
    POSITIVE LOGITS
     itself
    0.96
     varies
    0.91
     versus
    0.90
     depends
    0.88
     depended
    0.83
     compared
    0.83
     vary
    0.79
     beforehand
    0.77
     multiplied
    0.77
     relative
    0.77
    Activations Density 0.395%

    No Known Activations