© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 776
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or lack thereof

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "have"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilation
    -0.74
    stre
    -0.74
     guiName
    -0.59
    andan
    -0.58
     notwithstanding
    -0.57
    nown
    -0.57
     humili
    -0.55
     roar
    -0.55
     gasp
    -0.55
     Ruin
    -0.54
    POSITIVE LOGITS
     recourse
    0.95
     permission
    0.86
    stood
    0.83
     enough
    0.82
     been
    0.80
     access
    0.79
     sufficient
    0.79
     doubts
    0.75
     anymore
    0.75
     trouble
    0.74
    Activations Density 0.096%

    No Known Activations