© 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. 3-RES-JB
    11. 13353
    Prev
    Next
    INDEX
    Explanations

    keywords related to effectiveness or successful actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "effectively."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erer
    -0.81
    andro
    -0.76
    Ey
    -0.69
    yi
    -0.68
    bone
    -0.68
    ger
    -0.68
    erers
    -0.66
     Belt
    -0.62
    gow
    -0.62
     Tant
    -0.61
    POSITIVE LOGITS
     conclud
    0.81
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.80
     destro
    0.79
    ãĤ¼ãĤ¦ãĤ¹
    0.78
     exting
    0.78
    nown
    0.78
    姫
    0.76
     resil
    0.75
     communicate
    0.74
    ãĤ£
    0.74
    Activations Density 0.010%

    No Known Activations