© 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. 8-RES-JB
    11. 2451
    Prev
    Next
    INDEX
    Explanations

    phrases related to a contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    phrases characterized by evaluative or opinionated expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.70
    ukong
    -0.62
     newsp
    -0.60
    dit
    -0.60
    Laughs
    -0.59
    ologically
    -0.58
    bies
    -0.58
     welf
    -0.56
    iyah
    -0.55
    Introduced
    -0.55
    POSITIVE LOGITS
     nonetheless
    1.29
     nevertheless
    1.22
     hardly
    1.04
     still
    1.03
     unlikely
    1.02
     undeniable
    1.00
     undeniably
    0.99
     doubtful
    0.97
     unclear
    0.97
     certainly
    0.94
    Activations Density 0.172%

    No Known Activations