© 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. 3153
    Prev
    Next
    INDEX
    Explanations

    countries or entities responsible for actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that indicate responsibility or blame in a context of conflict or actions taken

    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
     RELEASE
    -0.72
    lif
    -0.70
    adesh
    -0.68
    udo
    -0.66
    ione
    -0.64
     Lif
    -0.64
     Habit
    -0.64
    Ut
    -0.62
     Congratulations
    -0.62
    UNE
    -0.62
    POSITIVE LOGITS
     responsible
    1.18
     blame
    1.08
     culprit
    1.07
     contributing
    1.05
    responsible
    1.00
     culp
    0.99
     influencing
    0.98
     contribut
    0.96
     perpetrators
    0.92
     motivating
    0.92
    Activations Density 0.972%

    No Known Activations