© 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. 8890
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles of entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a significant emotional or impactful experience

    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
     prosec
    -0.87
     favour
    -0.82
     withdraw
    -0.78
     predis
    -0.78
     revers
    -0.77
     neighb
    -0.77
     bid
    -0.76
     sil
    -0.76
     slope
    -0.76
     landsl
    -0.75
    POSITIVE LOGITS
    According
    1.67
    Consider
    1.60
    While
    1.46
    Instead
    1.46
    Whether
    1.45
    When
    1.45
    Earlier
    1.45
    During
    1.45
    After
    1.44
    Just
    1.43
    Activations Density 0.334%

    No Known Activations