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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11429
    Prev
    Next
    INDEX
    Explanations

    phrases starting with a speaker's continuation of a previous statement

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or structures in dialogue or narrative

    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
    wcsstore
    -0.81
    ãĥİ
    -0.71
    Frameworks
    -0.71
    ousands
    -0.70
    eros
    -0.70
    ĪĴ
    -0.67
    arta
    -0.67
    icial
    -0.63
    士
    -0.62
    ICAN
    -0.61
    POSITIVE LOGITS
     sarcast
    1.09
     omin
    0.96
     stating
    0.95
     summar
    0.92
     noting
    0.90
     quoting
    0.90
     stressing
    0.88
     reiter
    0.87
    :]
    0.87
     bluntly
    0.85
    Activations Density 0.112%

    No Known Activations