© 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. 2-RES-JB
    11. 12771
    Prev
    Next
    INDEX
    Explanations

    words related to unwanted actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to unwanted or unwelcome situations and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lass
    -0.85
    alach
    -0.82
    hetti
    -0.81
    ingham
    -0.81
    sis
    -0.80
    ophers
    -0.79
    mberg
    -0.79
    otide
    -0.78
    odynamics
    -0.78
    oled
    -0.78
    POSITIVE LOGITS
     unwanted
    1.13
     pregnancies
    1.10
     pregnancy
    0.91
     Parenthood
    0.87
    ãĤī
    0.82
     unwelcome
    0.78
     adolesc
    0.78
     Jagu
    0.72
     interference
    0.71
     offspring
    0.71
    Activations Density 0.011%

    No Known Activations