© 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. 0-RES-JB
    11. 23289
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases indicating clear visibility or presence

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating clear visibility or clarity of a situation or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bucks
    -0.76
    naire
    -0.71
    lua
    -0.67
    halla
    -0.65
    arian
    -0.64
    ttle
    -0.63
    jee
    -0.63
    ón
    -0.62
    pole
    -0.62
    rak
    -0.62
    POSITIVE LOGITS
     evident
    3.52
     apparent
    2.03
     evidenced
    1.65
     obvious
    1.65
     palpable
    1.54
     noticeable
    1.37
     visible
    1.26
     undeniable
    1.24
     observable
    1.22
     manifest
    1.22
    Activations Density 0.011%

    No Known Activations