© 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. 7477
    Prev
    Next
    INDEX
    Explanations

    phrases expressing judgment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    verbal phrases that indicate obligations or recommendations

    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
     syndrome
    -0.68
    vati
    -0.68
     Syndrome
    -0.66
    CI
    -0.65
     Cir
    -0.64
     Zah
    -0.62
     Patty
    -0.59
     improvised
    -0.58
     lucky
    -0.58
     Oss
    -0.58
    POSITIVE LOGITS
     be
    1.08
     suffice
    0.95
     ideally
    0.94
    ered
    0.92
     preced
    0.87
    nt
    0.86
     disqual
    0.85
     prompt
    0.81
    ering
    0.81
     inspire
    0.80
    Activations Density 0.084%

    No Known Activations