© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18457
    Prev
    Next
    INDEX
    Explanations

    entities with the word "new"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "new."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suspic
    -0.76
    uated
    -0.60
    staking
    -0.59
     Pav
    -0.59
    uate
    -0.58
     Reconstruction
    -0.56
     bulls
    -0.55
    istic
    -0.54
    ific
    -0.53
     Bravo
    -0.53
    POSITIVE LOGITS
    riter
    1.40
    ritten
    1.27
    estern
    1.19
    ITNESS
    1.09
    alker
    1.05
    esome
    1.05
    ORD
    1.04
    isdom
    1.03
    olf
    1.02
    erker
    1.01
    Activations Density 0.037%

    No Known Activations