© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 2767
    Prev
    Next
    INDEX
    Explanations

    sentences expressing a strong opinion or making a definitive statement

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     challeng
    -0.94
     organis
    -0.92
     analys
    -0.91
     massively
    -0.90
     concess
    -0.89
     foc
    -0.84
     horrend
    -0.81
     pse
    -0.81
    yip
    -0.80
    isable
    -0.79
    POSITIVE LOGITS
     Officials
    1.19
     Residents
    1.17
     Investigators
    1.11
     Neigh
    1.06
     Courtesy
    1.05
    Neigh
    1.04
     Neighbor
    1.02
     Officers
    1.02
    <|endoftext|>
    1.02
    Investigators
    1.01
    Activations Density 0.433%

    No Known Activations