© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15311
    Prev
    Next
    INDEX
    Explanations

    phrases related to introducing or warning about upcoming information

    oai_token-act-pair · gpt-3.5-turbo

    introductory phrases that indicate planning or preparation

    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
     Pier
    -0.62
    ãĥĩ
    -0.62
    oad
    -0.62
     diam
    -0.59
     outp
    -0.58
    omet
    -0.57
    aden
    -0.57
    vell
    -0.56
    iday
    -0.56
     succeeding
    -0.55
    POSITIVE LOGITS
     briefly
    0.89
     Explain
    0.84
     acknowledge
    0.84
     acquaint
    0.83
     introduce
    0.83
     recognize
    0.82
     clarify
    0.82
     remember
    0.81
     remind
    0.81
     let
    0.81
    Activations Density 0.184%

    No Known Activations