© 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. 4-RES-JB
    11. 19932
    Prev
    Next
    INDEX
    Explanations

    terms related to step-by-step instructions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Next" when followed by a number or instruction

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

    No Comments

    Negative Logits
     Feldman
    -0.85
     brim
    -0.75
     Erie
    -0.68
     Sinai
    -0.67
     sexes
    -0.67
     Ãĸ
    -0.66
     Stur
    -0.65
     Legions
    -0.64
     Stevens
    -0.62
     Sterling
    -0.61
    POSITIVE LOGITS
    Next
    0.86
     millenn
    0.86
    ļéĨĴ
    0.77
    Scene
    0.76
    ebus
    0.74
    ĻĤ
    0.73
    door
    0.72
     Generations
    0.71
     neighb
    0.71
    igon
    0.70
    Activations Density 0.030%

    No Known Activations