© 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. 2936
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral judgment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to accountability and recognition of truth

    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
     doesnt
    -0.92
    Scroll
    -0.91
     dont
    -0.90
     lol
    -0.86
     haha
    -0.86
    max
    -0.80
     tho
    -0.79
     didnt
    -0.77
     english
    -0.75
     wanna
    -0.75
    POSITIVE LOGITS
     acutely
    0.90
     undeniably
    0.88
     strikingly
    0.85
     contexts
    0.84
     profoundly
    0.83
     intimately
    0.83
     salient
    0.82
     constituted
    0.81
     fraught
    0.81
     firsthand
    0.79
    Activations Density 1.063%

    No Known Activations