© 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. 3-RES-JB
    11. 3579
    Prev
    Next
    INDEX
    Explanations

    words related to the usage or consumption of various items or substances

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to various forms of usage and application

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.79
     Lumpur
    -0.71
    çĦ
    -0.68
    wagen
    -0.60
    cknowled
    -0.60
     drawer
    -0.58
     Irving
    -0.58
     Blasio
    -0.58
    bye
    -0.57
    å§
    -0.57
    POSITIVE LOGITS
    catentry
    0.82
    olia
    0.72
    omnia
    0.72
    QL
    0.71
    ions
    0.68
    aneous
    0.65
    aukee
    0.64
    ION
    0.64
    enza
    0.63
    arious
    0.62
    Activations Density 0.050%

    No Known Activations