© 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. 4-RES-JB
    11. 2170
    Prev
    Next
    INDEX
    Explanations

    words related to expulsion or being kicked out

    oai_token-act-pair · gpt-3.5-turbo

    terms related to expulsion or removal

    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
    eyes
    -0.82
    phrine
    -0.73
    ourke
    -0.72
    aque
    -0.72
    trust
    -0.67
     amen
    -0.67
    Condition
    -0.67
     Needs
    -0.67
    ickey
    -0.64
    EY
    -0.64
    POSITIVE LOGITS
     expelled
    0.78
     expel
    0.74
    avorite
    0.72
    ¬¼
    0.69
     expulsion
    0.68
     disbelief
    0.66
    ploy
    0.64
    ESH
    0.63
    icted
    0.63
     Dresden
    0.63
    Activations Density 0.012%

    No Known Activations