© 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. 2-RES-JB
    11. 8451
    Prev
    Next
    INDEX
    Explanations

    mentions of high-tech related terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the high-tech industry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.65
     chapters
    -0.63
     herds
    -0.63
     Bagg
    -0.62
     awoken
    -0.60
     sober
    -0.59
     Cull
    -0.59
     Ramsey
    -0.59
     Dah
    -0.58
     Rowling
    -0.57
    POSITIVE LOGITS
    tech
    1.20
    Tech
    1.09
    technology
    0.89
    ronics
    0.89
    afety
    0.88
    tek
    0.86
     gadgets
    0.85
     Technology
    0.82
    iencies
    0.81
    idious
    0.81
    Activations Density 0.006%

    No Known Activations