© 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. 8-RES-JB
    11. 6132
    Prev
    Next
    INDEX
    Explanations

    words related to compatibility and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    references to compatibility, both in terms of technology and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vae
    -0.77
    isal
    -0.72
    ghazi
    -0.69
     Khe
    -0.68
    ibur
    -0.68
    pez
    -0.67
    esta
    -0.67
    ²¾
    -0.66
    vern
    -0.66
    quez
    -0.66
    POSITIVE LOGITS
    atibility
    0.91
    ably
    0.89
     Compatibility
    0.80
     compatibility
    0.79
    icut
    0.77
    ious
    0.77
    ivity
    0.76
    rehensive
    0.75
     compatible
    0.75
    atible
    0.73
    Activations Density 0.043%

    No Known Activations