© 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. 0-RES-JB
    6. 4958
    Prev
    Next
    INDEX
    Explanations

    numbers or numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical references, particularly those related to measurements or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ancest
    -0.66
     trough
    -0.63
     company
    -0.58
     taste
    -0.58
    itiz
    -0.58
     Viz
    -0.58
     snow
    -0.58
     intel
    -0.57
     soil
    -0.57
     biography
    -0.57
    POSITIVE LOGITS
    22
    3.16
    23
    2.43
    21
    2.37
    26
    2.16
    24
    2.12
    28
    2.10
    27
    1.99
    29
    1.98
    25
    1.96
    20
    1.96
    Activations Density 0.017%

    No Known Activations