© 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. 10002
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a mix of intriguing and unsettling experiences

    oai_token-act-pair · gpt-3.5-turbo

    connections and descriptors related to contrasting attributes or dualities

    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
    ESE
    -0.88
    Ws
    -0.81
    EStream
    -0.79
     Intake
    -0.76
    thood
    -0.75
    ppo
    -0.74
    uese
    -0.74
     Transmission
    -0.73
    ocobo
    -0.72
    ETS
    -0.71
    POSITIVE LOGITS
     exhilar
    1.35
     thrilling
    1.30
     awe
    1.27
     fascinating
    1.25
     hilarious
    1.21
     unforgettable
    1.21
     inspiring
    1.20
     frightening
    1.19
     poignant
    1.19
     exciting
    1.18
    Activations Density 0.169%

    No Known Activations