© 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. 4-RES-JB
    11. 17016
    Prev
    Next
    INDEX
    Explanations

    past tense verbs representing actions or events

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions and accomplishments

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

    No Comments

    Negative Logits
    ilaterally
    -0.69
    emale
    -0.66
     vulner
    -0.65
    stood
    -0.63
    atever
    -0.62
    xxxx
    -0.60
    ciating
    -0.58
    ographically
    -0.58
    ugen
    -0.56
    enegger
    -0.56
    POSITIVE LOGITS
     Slav
    0.54
     Psy
    0.52
     Coverage
    0.51
     Endless
    0.51
    ream
    0.50
     DEAD
    0.50
    zbollah
    0.50
    UTERS
    0.49
     ARM
    0.49
     Vulkan
    0.49
    Activations Density 0.217%

    No Known Activations