© 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. 20434
    Prev
    Next
    INDEX
    Explanations

    technical language related to the physical world

    oai_token-act-pair · gpt-3.5-turbo

    instances of requests or prompts related to actions or decisions made by individuals or groups

    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
    é¾
    -0.81
    CLUD
    -0.76
    OND
    -0.72
    hest
    -0.65
    foundland
    -0.65
    IQ
    -0.64
    worthy
    -0.62
    URI
    -0.58
    KN
    -0.58
    Condition
    -0.57
    POSITIVE LOGITS
    Instead
    1.15
     Instead
    1.08
    instead
    1.07
     instead
    0.99
     Rather
    0.86
    Rather
    0.83
     preferring
    0.78
     anymore
    0.77
     opting
    0.75
     let
    0.75
    Activations Density 0.094%

    No Known Activations