© 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. 12403
    Prev
    Next
    INDEX
    Explanations

    phrases related to large-scale projects and funding

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of projects, particularly in government and infrastructure 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
     Gam
    -0.73
    osate
    -0.68
    stones
    -0.65
    beck
    -0.64
    thirst
    -0.64
    \\\\\\\\
    -0.63
    ãĤ¦ãĤ¹
    -0.63
    sen
    -0.62
    DOS
    -0.62
     Brotherhood
    -0.61
    POSITIVE LOGITS
     involving
    0.95
    hips
    0.95
     abroad
    0.95
     undertaken
    0.93
    afety
    0.93
    hops
    0.93
    paces
    0.92
     affecting
    0.90
    uggest
    0.90
     projects
    0.86
    Activations Density 0.248%

    No Known Activations