© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5650
    Prev
    Next
    INDEX
    Explanations

    references to autographs and signed items

    oai_token-act-pair · gpt-3.5-turbo

    references to autographs and related signing events

    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
    bare
    -0.78
     anch
    -0.70
    growth
    -0.64
     slippery
    -0.63
    common
    -0.63
     Layer
    -0.62
     unexplained
    -0.61
    elsen
    -0.60
    NESS
    -0.60
     Lank
    -0.59
    POSITIVE LOGITS
    ographs
    1.54
    ograph
    1.37
    ographed
    1.00
    abilia
    0.99
     signings
    0.92
    enary
    0.90
    ograp
    0.90
    istration
    0.81
    enaries
    0.81
    iques
    0.79
    Activations Density 0.028%

    No Known Activations