© 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. 1486
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication or interaction between individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spoken."

    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
    Protect
    -0.71
    Eastern
    -0.65
    adj
    -0.62
    rather
    -0.60
    nen
    -0.59
    accompanied
    -0.57
    Ma
    -0.56
    abet
    -0.55
     TRANS
    -0.55
    NL
    -0.55
    POSITIVE LOGITS
     nor
    1.25
    yet
    1.07
     yet
    1.06
     anymore
    1.04
     anywhere
    1.00
     anything
    0.98
     anybody
    0.94
     since
    0.90
     dime
    0.89
     any
    0.88
    Activations Density 0.214%

    No Known Activations