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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21140
    Prev
    Next
    INDEX
    Explanations

    phrases indicating evaluation or potential in a professional context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate potential actions or outcomes related to individuals' roles or capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.76
    osate
    -0.67
     collapses
    -0.66
    ocide
    -0.66
    ilet
    -0.65
     Massacre
    -0.63
     defeats
    -0.62
     srfAttach
    -0.61
    ÙIJ
    -0.61
    ··
    -0.61
    POSITIVE LOGITS
     available
    1.14
     ready
    1.07
    available
    1.01
     receptive
    0.99
     suited
    0.98
     interested
    0.97
     fit
    0.95
     willing
    0.95
     recruited
    0.94
     keen
    0.94
    Activations Density 0.274%

    No Known Activations