© 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. 10-RES-JB
    11. 16579
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ingly', 'ously', 'fully' or 'ably'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that convey strong emotional or descriptive qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.91
    speech
    -0.81
    elsen
    -0.78
    afety
    -0.76
    icipated
    -0.75
    orem
    -0.75
    erto
    -0.75
    icip
    -0.74
    aea
    -0.74
    HAEL
    -0.72
    POSITIVE LOGITS
     inaccurate
    0.96
     inept
    0.96
     accurate
    0.93
     inefficient
    0.88
     addictive
    0.87
     devoid
    0.86
     reminiscent
    0.86
     naïve
    0.85
     incompetent
    0.84
     close
    0.84
    Activations Density 0.084%

    No Known Activations