© 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. 11-RES-JB
    11. 1051
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or decisions being taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to choices and directions taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.75
    cffff
    -0.69
    ategor
    -0.61
    Buzz
    -0.61
     liqu
    -0.61
     unrelated
    -0.61
     pandemonium
    -0.59
     Detected
    -0.59
    netflix
    -0.59
    Frag
    -0.58
    POSITIVE LOGITS
     undertook
    0.92
     adopt
    0.91
     undertake
    0.87
     take
    0.84
     embarked
    0.82
     pursue
    0.81
     adopted
    0.80
     follow
    0.80
    take
    0.79
     embark
    0.79
    Activations Density 0.149%

    No Known Activations