© 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. 7-RES-JB
    11. 13787
    Prev
    Next
    INDEX
    Explanations

    common words in a text related to the content or substance of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the contents of specific bags or containers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    roads
    -0.76
    ansson
    -0.71
    verbs
    -0.67
    ERA
    -0.67
     Humph
    -0.66
    frog
    -0.62
    asio
    -0.60
    opter
    -0.60
    leaders
    -0.60
    oglu
    -0.60
    POSITIVE LOGITS
     contents
    0.97
     thereof
    0.95
    paces
    0.88
    matter
    0.87
    pace
    0.84
     Contents
    0.83
    iveness
    0.82
    ĸļ
    0.81
     therein
    0.76
    hip
    0.76
    Activations Density 0.060%

    No Known Activations