© 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. 0-RES-JB
    11. 16353
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "rab" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "rab" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conception
    -0.62
     clients
    -0.62
     client
    -0.61
     size
    -0.61
     Performance
    -0.60
     clouds
    -0.59
     synchronization
    -0.59
     plan
    -0.58
     connection
    -0.56
     caching
    -0.56
    POSITIVE LOGITS
    rab
    4.69
    rub
    1.42
     Rab
    1.33
    rag
    1.22
    rap
    1.20
    rn
    1.19
    rav
    1.17
    raf
    1.15
    rb
    1.14
    ra
    1.14
    Activations Density 0.016%

    No Known Activations