© 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. 9-RES-JB
    11. 18395
    Prev
    Next
    INDEX
    Explanations

    statistics and demographic information

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and numerical data, particularly in statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ²¾
    -0.81
    asis
    -0.77
    ¬¼
    -0.71
    acas
    -0.67
     quarantine
    -0.66
    ãĥ¯ãĥ³
    -0.65
    ctions
    -0.64
    ģĸ
    -0.63
    usp
    -0.63
    arantine
    -0.62
    POSITIVE LOGITS
     averaging
    1.22
     compared
    1.15
     according
    1.13
     totaling
    1.11
     whereas
    1.09
     median
    1.06
     respectively
    1.03
    according
    0.98
     excluding
    0.98
    Chart
    0.96
    Activations Density 0.233%

    No Known Activations