© 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. 7-RES-JB
    11. 1636
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare settings and patient care

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to charitable actions and community service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bringer
    -0.67
    rez
    -0.65
    iece
    -0.64
     typo
    -0.63
    kb
    -0.63
     Krypt
    -0.62
     Kraken
    -0.62
    wered
    -0.61
    stan
    -0.61
     landfall
    -0.60
    POSITIVE LOGITS
    often
    1.09
    entimes
    0.93
    sometimes
    0.92
     often
    0.91
     Often
    0.87
     invariably
    0.86
     Occasionally
    0.86
    anwhile
    0.82
    usually
    0.81
    typically
    0.81
    Activations Density 1.059%

    No Known Activations