© 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. 9-RES-JB
    11. 16694
    Prev
    Next
    INDEX
    Explanations

    phrases related to additional or accompanying information or items

    oai_token-act-pair · gpt-3.5-turbo

    words indicating related or supplementary elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osate
    -0.93
    ifying
    -0.80
    erve
    -0.78
    Äį
    -0.76
    á½
    -0.76
    ruary
    -0.74
    tic
    -0.72
    usk
    -0.71
    enhagen
    -0.71
    tical
    -0.71
    POSITIVE LOGITS
     fields
    0.86
     disciplines
    0.85
     paperwork
    0.80
     mater
    0.79
     technologies
    0.78
     infrastructure
    0.78
     structures
    0.75
     literature
    0.75
     texts
    0.74
     tissues
    0.74
    Activations Density 0.116%

    No Known Activations