© 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. 7275
    Prev
    Next
    INDEX
    Explanations

    general information or details from news articles

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "More."

    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
    keeping
    -0.75
     2024
    -0.70
    liest
    -0.68
    Fram
    -0.67
    atan
    -0.67
    RL
    -0.65
    Enlarge
    -0.65
    itudes
    -0.65
    RN
    -0.64
    same
    -0.62
    POSITIVE LOGITS
     ado
    1.16
     Than
    1.10
     than
    1.04
     importantly
    1.03
     mature
    0.79
    than
    0.76
     important
    0.75
     sophisticated
    0.75
     extensive
    0.74
     stringent
    0.74
    Activations Density 0.035%

    No Known Activations