© 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. 16975
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or instructions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "with" accompanied by a variety of context

    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
    ulet
    -0.81
    quez
    -0.75
    hood
    -0.67
    eth
    -0.66
    stru
    -0.65
    ét
    -0.65
    oli
    -0.64
    handler
    -0.64
    fest
    -0.63
    economic
    -0.63
    POSITIVE LOGITS
     regard
    1.26
     impunity
    1.24
     regards
    1.15
     minimal
    1.14
     ease
    1.10
     respect
    1.09
    draw
    1.08
    stood
    1.04
     varying
    0.86
     caveats
    0.86
    Activations Density 0.135%

    No Known Activations