© 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. 11-RES-JB
    11. 2856
    Prev
    Next
    INDEX
    Explanations

    phrases related to next-generation technology or products

    oai_token-act-pair · gpt-3.5-turbo

    references to next-generation technology and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vaughn
    -0.66
     Concord
    -0.66
     Lester
    -0.64
     Schwe
    -0.63
     Cah
    -0.62
     âĶľ
    -0.62
     Patton
    -0.62
     Coulter
    -0.60
     bart
    -0.59
     alone
    -0.59
    POSITIVE LOGITS
    generation
    1.57
    gen
    1.34
    door
    1.22
     generation
    1.09
    wave
    1.03
    century
    1.01
    Gener
    1.01
    level
    1.00
    Gen
    0.97
    largest
    0.94
    Activations Density 0.057%

    No Known Activations