© 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. 4-RES-JB
    11. 12244
    Prev
    Next
    INDEX
    Explanations

    centers or institutions with a specific focus or purpose

    oai_token-act-pair · gpt-3.5-turbo

    references to various research or institutional centers

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

    No Comments

    Negative Logits
    earable
    -0.81
    Merit
    -0.73
    RESULTS
    -0.73
    agging
    -0.72
    é¾į
    -0.67
    arser
    -0.67
    ãģĦ
    -0.65
    mx
    -0.64
    Else
    -0.64
    seys
    -0.64
    POSITIVE LOGITS
    piece
    0.99
     Centre
    0.84
    gomery
    0.82
    ablishment
    0.79
    pieces
    0.78
    tenance
    0.71
     enrol
    0.69
     paran
    0.68
     fielder
    0.67
    loe
    0.66
    Activations Density 0.011%

    No Known Activations