© 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. 4-RES-JB
    11. 20437
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "milestone."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "milestone" and related terms

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

    No Comments

    Negative Logits
    ©¶æ
    -1.04
    opoly
    -0.78
    oks
    -0.77
    obar
    -0.75
    otto
    -0.72
    ivia
    -0.71
    odge
    -0.71
    ately
    -0.71
    ateur
    -0.71
    olls
    -0.70
    POSITIVE LOGITS
     milestones
    1.15
     milestone
    1.14
    posts
    0.86
     accomplishment
    0.82
     achievement
    0.81
    enance
    0.76
     hurdle
    0.73
     achievements
    0.71
     celebrations
    0.70
     completion
    0.69
    Activations Density 0.009%

    No Known Activations