© 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. 537
    Prev
    Next
    INDEX
    Explanations

    dates in the format of month and day

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific dates or numerical references

    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
    amaru
    -0.82
    allo
    -0.80
    algia
    -0.75
    rophe
    -0.74
    ensibly
    -0.73
    achu
    -0.72
    ĸļ
    -0.72
    reads
    -0.71
    olate
    -0.70
    atem
    -0.70
    POSITIVE LOGITS
    00
    1.08
    nm
    0.94
    80
    0.86
    th
    0.85
    mins
    0.83
    nd
    0.78
    iology
    0.76
    MHz
    0.73
    70
    0.72
    30
    0.72
    Activations Density 0.024%

    No Known Activations