© 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. 8-RES-JB
    11. 2585
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles preceded by the word "the"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "The."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eno
    -0.79
    iably
    -0.75
    leeve
    -0.73
    ����
    -0.73
    govtrack
    -0.69
    whatever
    -0.68
    âĹ¼
    -0.67
    akable
    -0.67
    tackle
    -0.67
    abuse
    -0.67
    POSITIVE LOGITS
     remainder
    1.18
    oret
    1.08
     largest
    1.05
     earliest
    1.03
     entire
    1.01
     following
    1.00
     newest
    1.00
     goal
    0.98
     purpose
    0.96
     latest
    0.96
    Activations Density 0.478%

    No Known Activations