© 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. 10-RES-JB
    11. 20227
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships, interactions, and actions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their relationships within phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    requently
    -0.89
    iosyncr
    -0.80
    ophon
    -0.79
    atility
    -0.77
    asury
    -0.73
    ourses
    -0.72
     guiActiveUn
    -0.68
    ourse
    -0.67
    visors
    -0.66
    utive
    -0.66
    POSITIVE LOGITS
     huh
    1.62
     eh
    1.49
     haha
    1.30
     yeah
    1.22
     right
    1.15
     lol
    1.14
     blah
    1.14
     ya
    1.10
     anyways
    1.08
     oh
    1.07
    Activations Density 0.309%

    No Known Activations