© 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. 10574
    Prev
    Next
    INDEX
    Explanations

    phrases related to alternative options or choices

    oai_token-act-pair · gpt-3.5-turbo

    words related to tasks and actions

    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
     Nobody
    -0.83
     nobody
    -0.81
    Nobody
    -0.75
     hadn
    -0.72
    itiveness
    -0.66
    hest
    -0.64
    Five
    -0.63
    nothing
    -0.61
    Seven
    -0.61
    Nine
    -0.60
    POSITIVE LOGITS
     alternatively
    1.22
     Alternatively
    1.05
     optionally
    1.04
    Alternatively
    0.99
     substituted
    0.94
     utilize
    0.94
     depending
    0.89
    yip
    0.89
     util
    0.88
     utilized
    0.85
    Activations Density 0.494%

    No Known Activations