© 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. 2-RES-JB
    11. 11034
    Prev
    Next
    INDEX
    Explanations

    mentions of authorities or officials in the context of news or reports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of authorities or official entities involved in events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pc
    -0.64
     platinum
    -0.64
    present
    -0.62
     behold
    -0.61
     life
    -0.61
    fur
    -0.60
     present
    -0.60
     face
    -0.59
    çĦ
    -0.59
     towel
    -0.58
    POSITIVE LOGITS
     Differences
    1.02
     Definition
    0.98
     Benefits
    0.93
     Locations
    0.90
     Definitions
    0.88
     Costs
    0.88
     Procedures
    0.88
     Difference
    0.88
     Picks
    0.86
     Files
    0.86
    Activations Density 0.256%

    No Known Activations