© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2854
    Prev
    Next
    INDEX
    Explanations

    years or specific time references

    oai_token-act-pair · gpt-3.5-turbo

    historical dates and milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snipp
    -0.77
    umbn
    -0.66
    imore
    -0.61
    ITION
    -0.59
    Jackson
    -0.58
     Pru
    -0.57
    IPP
    -0.55
    VALUE
    -0.55
     dy
    -0.55
     Jugg
    -0.55
    POSITIVE LOGITS
     onwards
    0.95
     onward
    0.87
    â̲
    0.82
     inception
    0.69
    quist
    0.61
    staking
    0.61
    .
    0.61
     captivity
    0.60
    cation
    0.60
    ties
    0.60
    Activations Density 0.129%

    No Known Activations