Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 17531
    Prev
    Next
    INDEX
    Explanations

    keywords related to compatibility between different devices or systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to compatibility and incompatibility

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

    No Comments

    Negative Logits
    esville
    -0.80
    arcity
    -0.74
    Downloadha
    -0.73
    vern
    -0.73
    pez
    -0.72
    mort
    -0.70
    bull
    -0.70
    dream
    -0.69
    hunt
    -0.69
    otonin
    -0.69
    POSITIVE LOGITS
     compatibility
    0.98
    atibility
    0.87
     Compatibility
    0.87
     compatible
    0.85
    Offline
    0.75
     compat
    0.73
     compliant
    0.71
    atible
    0.71
    nesses
    0.70
     interoper
    0.70
    Activations Density 0.019%

    No Known Activations