© 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. 2224
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic studies or topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of"

    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
    etsk
    -0.77
    earchers
    -0.67
    wall
    -0.67
    cedented
    -0.67
    ħĭ
    -0.66
     [&
    -0.65
    DragonMagazine
    -0.65
    ername
    -0.63
    fal
    -0.63
     jaws
    -0.63
    POSITIVE LOGITS
     warfare
    0.86
     Warfare
    0.80
    version
    0.76
    effic
    0.74
    heres
    0.73
     Ruin
    0.70
    each
    0.69
    efficiency
    0.66
    icial
    0.64
     course
    0.63
    Activations Density 0.209%

    No Known Activations