© 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. 9-RES-JB
    11. 10142
    Prev
    Next
    INDEX
    Explanations

    phrases that express ease or difficulty

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express simplicity or ease in performing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dur
    -0.81
     Relief
    -0.69
    ELD
    -0.68
    allowed
    -0.68
    DAQ
    -0.66
     Balls
    -0.66
    cedented
    -0.66
     favors
    -0.64
     Brach
    -0.62
    eting
    -0.62
    POSITIVE LOGITS
     forget
    1.18
     mistake
    1.05
     confuse
    1.02
     miscon
    1.01
     navigate
    1.01
     identify
    1.00
     overlook
    0.96
     visualize
    0.96
     learn
    0.95
     misinterpret
    0.95
    Activations Density 0.075%

    No Known Activations