© 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. 2-RES-JB
    11. 17380
    Prev
    Next
    INDEX
    Explanations

    phrases associated with email newsletter sign-ups

    oai_token-act-pair · gpt-3.5-turbo

    repetitive requests or prompts related to user interaction

    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
    senal
    -0.86
    Closure
    -0.63
    ription
    -0.63
    rovers
    -0.61
    dash
    -0.61
     Huntington
    -0.61
    ability
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
    ARC
    -0.59
    ascus
    -0.58
    POSITIVE LOGITS
     note
    0.78
     Please
    0.76
    atre
    0.75
    OGR
    0.74
     advise
    0.72
     pardon
    0.71
     forgive
    0.69
     underestimate
    0.67
     Note
    0.67
     enter
    0.66
    Activations Density 0.014%

    No Known Activations