© 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. 2-RES-JB
    6. 17258
    Prev
    Next
    INDEX
    Explanations

    numerical terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to numbers and numerical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.84
    ACP
    -0.71
    hov
    -0.66
     Thoughts
    -0.64
    tnc
    -0.63
    ̶
    -0.63
    wards
    -0.63
     Butt
    -0.63
    Closure
    -0.63
    HAM
    -0.63
    POSITIVE LOGITS
     numer
    1.09
    umbers
    0.95
    umer
    0.86
    abulary
    0.85
    ationally
    0.84
    alling
    0.81
    orthern
    0.79
    igr
    0.79
    ically
    0.76
    ancial
    0.74
    Activations Density 0.014%

    No Known Activations