© 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. 8-RES-JB
    11. 19411
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases describing a negative judgment or critique

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating consequences or implications

    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
    ARM
    -0.66
    949
    -0.65
    Interested
    -0.65
    LOCK
    -0.64
    perse
    -0.63
    NV
    -0.63
    Dist
    -0.63
    amus
    -0.60
    RL
    -0.60
    rament
    -0.60
    POSITIVE LOGITS
     behalf
    1.60
     occasion
    1.32
    erous
    1.17
     steroids
    1.11
    etime
    1.08
     occasions
    1.03
    eday
    1.02
    eness
    1.01
    shore
    0.96
    slaught
    0.96
    Activations Density 0.299%

    No Known Activations