© 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. 3335
    Prev
    Next
    INDEX
    Explanations

    information related to lists or bullet points in a document

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to lists or compilations of items

    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
    voc
    -0.57
    lication
    -0.56
     ç¥ŀ
    -0.54
    akuya
    -0.52
     whatsoever
    -0.52
    iour
    -0.51
     valves
    -0.51
     disciples
    -0.51
     pupils
    -0.51
    prot
    -0.51
    POSITIVE LOGITS
     infographic
    1.01
     rundown
    0.89
     compiled
    0.88
     POLITICO
    0.87
     excerpts
    0.86
     below
    0.86
     HuffPost
    0.84
     charts
    0.83
     chron
    0.82
     slideshow
    0.80
    Activations Density 1.075%

    No Known Activations