© 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. 12703
    Prev
    Next
    INDEX
    Explanations

    expressions related to politics and opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of conflict and opposition

    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
     âĢº
    -0.68
    )",
    -0.67
    Enlarge
    -0.66
    Previously
    -0.64
    "),
    -0.63
    ),"
    -0.63
    ")
    -0.63
    Initially
    -0.62
    ","
    -0.62
    earable
    -0.60
    POSITIVE LOGITS
     coward
    0.78
     goddamn
    0.74
     damned
    0.74
     patri
    0.72
     Genocide
    0.72
     hypocritical
    0.71
     dehuman
    0.71
     hypocrisy
    0.71
     fools
    0.70
     fucking
    0.70
    Activations Density 2.242%

    No Known Activations