© 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. 3-RES-JB
    11. 23156
    Prev
    Next
    INDEX
    Explanations

    dates in the format year-year that suggest a specific time period or event

    oai_token-act-pair · gpt-3.5-turbo

    specific years, particularly in the 1990s

    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
    Tu
    -0.73
    semb
    -0.69
    hed
    -0.66
    tro
    -0.65
    lying
    -0.65
    ent
    -0.60
    haar
    -0.60
    holder
    -0.59
    friends
    -0.58
    sing
    -0.58
    POSITIVE LOGITS
    ĸļ
    0.94
    theless
    0.78
    å¹
    0.75
    uncture
    0.74
    -'
    0.72
    ovies
    0.70
     onwards
    0.70
    ãĥ¼ãĥ«
    0.69
    ãĥ£
    0.66
     onward
    0.66
    Activations Density 0.016%

    No Known Activations