© 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. 10-RES-JB
    11. 12390
    Prev
    Next
    INDEX
    Explanations

    sentences discussing different issues or topics

    oai_token-act-pair · gpt-3.5-turbo

    statements or sentences that present significant observations or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affili
    -0.74
     neighb
    -0.71
    kefeller
    -0.69
    ŃĶ
    -0.66
    staking
    -0.66
    isher
    -0.66
     charact
    -0.65
     strugg
    -0.64
     accomp
    -0.64
    opian
    -0.63
    POSITIVE LOGITS
     Whilst
    1.44
     Again
    1.35
     While
    1.29
     Currently
    1.29
     Obviously
    1.26
     Normally
    1.25
     Although
    1.24
     Unless
    1.23
     Firstly
    1.23
     Apparently
    1.22
    Activations Density 0.290%

    No Known Activations