© 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. 8474
    Prev
    Next
    INDEX
    Explanations

    links, instructions, and options provided in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating capability or options

    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
    ĸļ
    -0.68
    Initialized
    -0.59
    ruction
    -0.59
     Destruction
    -0.57
    ocracy
    -0.56
    ulner
    -0.56
    jab
    -0.54
    unda
    -0.53
    Files
    -0.53
     supposedly
    -0.52
    POSITIVE LOGITS
     someday
    1.13
     tempted
    0.79
     inadvertently
    0.76
    xus
    0.75
     depending
    0.72
     underest
    0.71
    ivably
    0.71
     somew
    0.70
     misunder
    0.69
    depending
    0.68
    Activations Density 0.340%

    No Known Activations