© 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. 4-RES-JB
    11. 6803
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names that are associated with different events or people, especially those related to interviews or collaborations

    oai_token-act-pair · gpt-3.5-turbo

    the word "for" used in various contexts

    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
    ttle
    -0.72
    aults
    -0.70
    Fle
    -0.68
    plate
    -0.64
    fleet
    -0.64
    hess
    -0.63
    Ohio
    -0.62
    illin
    -0.62
    Strange
    -0.62
    §
    -0.61
    POSITIVE LOGITS
    geries
    1.22
     example
    1.05
    ked
    1.03
    bidden
    1.01
     instance
    0.98
    gery
    0.96
     purposes
    0.89
    gotten
    0.83
     centuries
    0.83
     whom
    0.79
    Activations Density 0.275%

    No Known Activations