© 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. 11-RES-JB
    11. 7546
    Prev
    Next
    INDEX
    Explanations

    calls to action in the form of signing up for newsletters or alerts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to newsletters and subscription prompts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suffice
    -0.72
     discour
    -0.60
     Principles
    -0.59
    ;;;;;;;;;;;;
    -0.59
     unres
    -0.59
    éĹ
    -0.58
     Altern
    -0.57
     Representative
    -0.57
     Cho
    -0.57
    llor
    -0.56
    POSITIVE LOGITS
    awei
    0.70
    ythm
    0.67
     gadget
    0.63
    iPhone
    0.63
     gadgets
    0.62
     developments
    0.62
     celeb
    0.61
    alde
    0.60
    okia
    0.59
     Esports
    0.59
    Activations Density 0.070%

    No Known Activations