© 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. 5596
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to unique or characteristic elements

    oai_token-act-pair · gpt-3.5-turbo

    references to unique characteristics or trademarks associated with items or individuals

    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
    aiman
    -0.85
    isen
    -0.81
    agan
    -0.77
    á½
    -0.77
    nih
    -0.76
    ASC
    -0.74
    ulu
    -0.74
    astern
    -0.73
    awar
    -0.73
    uga
    -0.71
    POSITIVE LOGITS
     signature
    0.84
     breaker
    0.81
     accomplishment
    0.74
     style
    0.73
     achievement
    0.71
     hallmark
    0.69
    board
    0.67
    zag
    0.67
     phrase
    0.66
    ATURE
    0.66
    Activations Density 0.017%

    No Known Activations