© 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. 6-RES-JB
    11. 9313
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts between different groups or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to comparative groups or counterparts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    faith
    -0.64
    ":"/
    -0.63
    aw
    -0.62
    ãĥĻ
    -0.62
    attribute
    -0.60
    wrong
    -0.60
    èĢħ
    -0.59
    ="/
    -0.58
    urai
    -0.58
    OTT
    -0.58
    POSITIVE LOGITS
     counterparts
    1.02
     predecessors
    0.92
     predec
    0.81
     peers
    0.77
     wont
    0.76
     contemporaries
    0.75
     predecessor
    0.69
     indo
    0.66
     competitors
    0.65
     olds
    0.64
    Activations Density 0.426%

    No Known Activations