© 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 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. 11-RES-JB
    11. 14994
    Prev
    Next
    INDEX
    Explanations

    text related to organizations, projects, and medical conditions, particularly those centered around support and assistance

    oai_token-act-pair · gpt-3.5-turbo

    references to established organizations and their programs or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     space
    -0.85
     adm
    -0.84
     regards
    -0.78
     alien
    -0.77
     superf
    -0.77
     erratic
    -0.77
     overd
    -0.77
     outer
    -0.76
     tall
    -0.76
     incarn
    -0.76
    POSITIVE LOGITS
    MAC
    1.64
    formerly
    1.62
    NYSE
    1.56
    NRS
    1.54
    PDF
    1.51
    UGC
    1.51
    KA
    1.50
    AMS
    1.50
    IPS
    1.49
    RIC
    1.49
    Activations Density 0.068%

    No Known Activations