© 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. 3295
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of 'passing' such as the passing of time, the passing of individuals, or the passing of information

    oai_token-act-pair · gpt-3.5-turbo

    references to transitions, changes, or experiences of loss

    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
    WARE
    -0.76
     reperto
    -0.75
    Ô
    -0.74
    CIA
    -0.69
    ashtra
    -0.68
     istg
    -0.67
    Catalog
    -0.67
    KO
    -0.66
    aspers
    -0.65
    KK
    -0.64
    POSITIVE LOGITS
     course
    1.01
     sorts
    0.89
    osphere
    0.77
     Nanto
    0.69
    liest
    0.68
    icial
    0.64
     aisle
    0.62
     Horus
    0.61
    rium
    0.61
    course
    0.60
    Activations Density 0.690%

    No Known Activations