© 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. 23536
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the material something is made from

    oai_token-act-pair · gpt-3.5-turbo

    references to the materials or sources used in making items

    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
    osponsors
    -0.89
    heastern
    -0.74
    veland
    -0.74
    doms
    -0.70
     ushered
    -0.69
    yip
    -0.68
    merce
    -0.68
    show
    -0.68
    akia
    -0.68
    tn
    -0.67
    POSITIVE LOGITS
     scratch
    1.32
     mole
    0.82
    ãĤ©
    0.80
     tissue
    0.72
     humble
    0.71
     vegetable
    0.71
     materials
    0.70
     LEGO
    0.70
     fiber
    0.69
     pure
    0.69
    Activations Density 0.146%

    No Known Activations