© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14976
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential disaster or chaos

    oai_token-act-pair · gpt-3.5-turbo

    metaphorical expressions related to decline or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [+
    -0.74
    TF
    -0.62
    SF
    -0.58
    OTOS
    -0.58
     Uz
    -0.57
    eg
    -0.56
    pelled
    -0.56
    Supp
    -0.54
     Quality
    -0.54
    NZ
    -0.54
    POSITIVE LOGITS
    ometer
    0.82
    wagon
    0.81
    wark
    0.72
    ousel
    0.71
    bowl
    0.70
     coaster
    0.69
    otomy
    0.69
    pit
    0.68
    pins
    0.68
    vine
    0.67
    Activations Density 0.390%

    No Known Activations