© 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. 4-RES-JB
    11. 541
    Prev
    Next
    INDEX
    Explanations

    words related to eccentricity and quirkiness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to eccentricity and unconventional behavior

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

    No Comments

    Negative Logits
    vation
    -0.70
    ylon
    -0.70
    Indust
    -0.69
    FORE
    -0.68
    adows
    -0.68
    din
    -0.67
     istg
    -0.66
    horn
    -0.66
    light
    -0.66
    onds
    -0.66
    POSITIVE LOGITS
     quirks
    1.27
     idiosyncr
    0.98
     antics
    0.93
     twists
    0.90
     eccentric
    0.87
     whims
    0.84
    odox
    0.81
    worldly
    0.79
     quirky
    0.79
     twist
    0.77
    Activations Density 0.028%

    No Known Activations