© 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. 11478
    Prev
    Next
    INDEX
    Explanations

    sentences discussing trust and interpersonal relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases and discussions related to trust and belief systems

    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
     scrambling
    -0.55
    MSN
    -0.49
    ubb
    -0.49
     decorated
    -0.49
     cart
    -0.49
    berra
    -0.48
    raft
    -0.48
    âķIJ
    -0.48
     cancell
    -0.48
     scrap
    -0.48
    POSITIVE LOGITS
     Therefore
    0.61
    Therefore
    0.57
     Answer
    0.56
     ..."
    0.52
    hovah
    0.51
    &&
    0.51
    instead
    0.51
     THEN
    0.51
     Allow
    0.49
    aido
    0.49
    Activations Density 1.233%

    No Known Activations