© 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. 8-RES-JB
    11. 16858
    Prev
    Next
    INDEX
    Explanations

    phrases indicating moving forward with a plan or action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "go ahead" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brid
    -0.80
    othy
    -0.72
    igi
    -0.72
    ellow
    -0.70
    rador
    -0.69
    TOR
    -0.69
    anooga
    -0.69
    OTS
    -0.69
    Net
    -0.69
    itu
    -0.69
    POSITIVE LOGITS
     unnoticed
    0.81
     undet
    0.76
     blindly
    0.75
     willingly
    0.71
    acht
    0.70
     anyway
    0.68
     indefinitely
    0.65
     Steps
    0.64
     voluntarily
    0.63
     unsc
    0.63
    Activations Density 0.024%

    No Known Activations