© 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. 8-RES-JB
    11. 2422
    Prev
    Next
    INDEX
    Explanations

    different operational modes or settings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to modes and types of functioning or operation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Liberties
    -0.84
     Sparks
    -0.68
    AGES
    -0.67
    flies
    -0.67
    PsyNetMessage
    -0.64
    eries
    -0.63
     nerves
    -0.63
    OSH
    -0.63
    owsky
    -0.63
    bec
    -0.62
    POSITIVE LOGITS
     intermediate
    1.13
     semi
    1.05
     multip
    1.05
     Semi
    0.95
     sem
    0.92
     multic
    0.91
     Triple
    0.88
     Intermediate
    0.86
     medium
    0.84
     ultra
    0.84
    Activations Density 0.517%

    No Known Activations