© 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. 7-RES-JB
    11. 21824
    Prev
    Next
    INDEX
    Explanations

    phrases related to consequences or predictions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to negative consequences or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reception
    -0.64
     Paran
    -0.63
     Malays
    -0.62
     Lithuan
    -0.62
     Lindsey
    -0.62
     Ivy
    -0.61
     Malaysian
    -0.61
     Monteneg
    -0.60
    htaking
    -0.58
     Zika
    -0.58
    POSITIVE LOGITS
     automatically
    0.86
     suddenly
    0.79
    Ł
    0.76
     indistinguishable
    0.74
    İ
    0.71
     disappears
    0.70
    Untitled
    0.70
     spontaneously
    0.70
     becomes
    0.70
     magically
    0.69
    Activations Density 0.564%

    No Known Activations