© 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. 18625
    Prev
    Next
    INDEX
    Explanations

    mentions of people and their roles/functions in a community

    oai_token-act-pair · gpt-3.5-turbo

    topics related to community involvement and contributions

    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
    instead
    -0.67
    rather
    -0.59
     compared
    -0.58
    ularity
    -0.55
     Versus
    -0.55
     Instead
    -0.54
     Compared
    -0.53
     compares
    -0.53
    833
    -0.53
    iverse
    -0.53
    POSITIVE LOGITS
     thereto
    0.82
    cellaneous
    0.71
    catentry
    0.65
     commentary
    0.64
    alsa
    0.62
    tails
    0.60
    monds
    0.60
     reinforcements
    0.59
     conting
    0.59
    cill
    0.58
    Activations Density 0.549%

    No Known Activations