© 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 EvalsExportsinterp-engineNEWAPI 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. 2754
    Prev
    Next
    INDEX
    Explanations

    adjectives referring to quality or significance

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptive phrases that convey significant emotional or evaluative weight

    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
    aneers
    -0.91
    »Ĵ
    -0.81
    IDES
    -0.80
    ahs
    -0.79
    icons
    -0.78
    dor
    -0.76
    racuse
    -0.76
    endants
    -0.74
    viks
    -0.74
    onds
    -0.72
    POSITIVE LOGITS
     territory
    1.27
     fodder
    1.08
     stuff
    1.07
     nonsense
    1.04
     enough
    1.04
     insanity
    0.97
     behavior
    0.97
     advice
    0.94
     folly
    0.93
     stupidity
    0.93
    Activations Density 0.306%

    No Known Activations