© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15444
    Prev
    Next
    INDEX
    Explanations

    words related to clubs or communities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of subsidies and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embr
    -0.70
    aging
    -0.68
    agnetic
    -0.66
    gow
    -0.64
     Attribution
    -0.63
     Ogre
    -0.63
    ë
    -0.62
     nort
    -0.62
    Ocean
    -0.61
     Ragnarok
    -0.60
    POSITIVE LOGITS
    bish
    1.16
    bing
    1.06
    ubs
    0.93
    bies
    0.93
    culosis
    0.92
    bie
    0.84
    bery
    0.84
    bers
    0.83
    isine
    0.82
    bed
    0.82
    Activations Density 0.016%

    No Known Activations