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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 929
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning specific locations, particularly places with the word "Oak" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Oak" in various contexts

    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
    enance
    -0.96
    è¦ļéĨĴ
    -0.78
    ozyg
    -0.73
    ĸļ
    -0.68
     exagger
    -0.67
    advertisement
    -0.67
    anse
    -0.66
    anmar
    -0.66
    glomer
    -0.65
    SHIP
    -0.64
    POSITIVE LOGITS
    sterdam
    1.20
    vale
    1.06
    ridge
    1.06
    wood
    1.02
    leaf
    1.01
     Ridge
    0.99
    leigh
    0.97
    bridge
    0.95
    hurst
    0.92
    tree
    0.92
    Activations Density 0.022%

    No Known Activations