© 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. 5589
    Prev
    Next
    INDEX
    Explanations

    comparisons or explanations of a specific topic or situation comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases that use "in that" to introduce explanations or justifications

    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
    asters
    -0.80
    ormons
    -0.76
    rior
    -0.71
    Guard
    -0.71
    inx
    -0.64
     srfAttach
    -0.63
    izont
    -0.62
    IDES
    -0.62
    quit
    -0.61
    ono
    -0.61
    POSITIVE LOGITS
     vein
    1.12
     regard
    1.02
     particular
    0.99
     vicinity
    0.97
     same
    0.92
     timeframe
    0.84
     manner
    0.83
     circumstance
    0.81
     area
    0.80
     fateful
    0.79
    Activations Density 0.045%

    No Known Activations