© 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. 7-RES-JB
    11. 21100
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific elements, possibly related to chemistry or materials

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships or connections between 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
     prices
    -0.63
     passers
    -0.63
     CBI
    -0.63
     cf
    -0.62
    jad
    -0.61
     partName
    -0.60
     ridic
    -0.59
     multiplication
    -0.59
     ss
    -0.59
     Syndicate
    -0.57
    POSITIVE LOGITS
    rontal
    1.34
    sky
    1.23
    ortunately
    1.07
    eatures
    0.96
    ollow
    0.95
    lav
    0.95
    unction
    0.95
    riend
    0.94
    ield
    0.94
     course
    0.93
    Activations Density 0.037%

    No Known Activations