© 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. 0-RES-JB
    11. 11275
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a collective or group action

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confirmation
    -0.65
     Lovely
    -0.59
    rick
    -0.59
     disguise
    -0.58
    old
    -0.57
    jar
    -0.55
    ss
    -0.55
     removal
    -0.55
     old
    -0.54
     replacement
    -0.54
    POSITIVE LOGITS
     collectively
    3.78
     individually
    1.62
     collective
    1.55
     jointly
    1.50
     respectively
    1.30
    collect
    1.29
    together
    1.28
     together
    1.24
     unanimously
    1.19
     toget
    1.09
    Activations Density 0.016%

    No Known Activations