© 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. 0-RES-JB
    11. 10264
    Prev
    Next
    INDEX
    Explanations

    words related to various forms of aggression or confrontation

    oai_token-act-pair · gpt-3.5-turbo

    the word forms related to "acked" and "attered."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tsukuyomi
    -0.65
     principle
    -0.63
     cal
    -0.62
     conservation
    -0.61
     Vine
    -0.61
     clar
    -0.61
     Bach
    -0.60
     breeding
    -0.60
     question
    -0.60
     here
    -0.59
    POSITIVE LOGITS
    acked
    4.15
    acks
    2.31
    acking
    2.16
    acker
    1.89
    ACK
    1.83
    ackers
    1.58
    ushed
    1.51
    ack
    1.48
    icked
    1.30
    umped
    1.27
    Activations Density 0.005%

    No Known Activations