© 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. 10-RES-JB
    6. 10744
    Prev
    Next
    INDEX
    Explanations

    phrases indicating likelihood or probability of an event happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asar
    -0.68
    instead
    -0.67
     Sands
    -0.59
    urches
    -0.59
     Tanz
    -0.58
     Recording
    -0.57
     Tsukuyomi
    -0.56
    Afee
    -0.56
     Peninsula
    -0.55
     WRITE
    -0.54
    POSITIVE LOGITS
     importantly
    1.25
     likely
    1.21
     certainly
    1.14
     definitely
    1.13
     notably
    1.12
     assured
    1.08
    likely
    1.07
     prominently
    1.06
    afa
    1.02
     Likely
    0.97
    Activations Density 0.041%

    No Known Activations