© 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. 3-RES-JB
    6. 11170
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to aggregating or bringing together various elements or data

    oai_token-act-pair · gpt-3.5-turbo

    terms related to aggregation or the process of combining multiple elements into a single entity

    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
    ney
    -0.76
    nen
    -0.76
    ne
    -0.75
    neg
    -0.72
    pher
    -0.71
    chen
    -0.71
    nee
    -0.70
    stroke
    -0.70
    enko
    -0.69
    eland
    -0.67
    POSITIVE LOGITS
     aggreg
    1.18
     aggregation
    1.13
     aggregate
    1.05
    regate
    0.93
    ãĥ¼ãĥĨãĤ£
    0.77
    ulates
    0.76
     sum
    0.75
    ulative
    0.72
     bundles
    0.71
     conglomer
    0.66
    Activations Density 0.014%

    No Known Activations