© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3249
    Prev
    Next
    INDEX
    Explanations

    terms related to financial matters, such as financing, investments, and plans

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to financial success and completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meanings
    -0.58
     liberty
    -0.58
     dumb
    -0.54
     brains
    -0.54
     creators
    -0.54
     kinds
    -0.53
     memories
    -0.53
     mistaken
    -0.53
     Alibaba
    -0.53
     Intelligent
    -0.53
    POSITIVE LOGITS
    ancing
    1.23
    anced
    1.20
    ishers
    1.17
    isher
    1.11
    agle
    1.11
    anc
    1.08
    ishing
    1.08
    icky
    1.06
    ances
    1.04
    anz
    1.01
    Activations Density 0.023%

    No Known Activations