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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16745
    Prev
    Next
    INDEX
    Explanations

    words related to improvement or skill development, particularly through practice or refinement

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "honoring" or recognition

    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
    TY
    -0.79
     Franch
    -0.76
    FACE
    -0.71
    TPS
    -0.70
    mia
    -0.69
     Yamato
    -0.69
    IDE
    -0.68
    FAULT
    -0.66
     Esc
    -0.65
    BOOK
    -0.65
    POSITIVE LOGITS
    olulu
    1.00
     hon
    0.96
    animous
    0.89
    ours
    0.88
    rie
    0.82
    oing
    0.82
    ision
    0.82
    itives
    0.81
    edo
    0.80
    orem
    0.79
    Activations Density 0.027%

    No Known Activations