© 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. 16275
    Prev
    Next
    INDEX
    Explanations

    uppercase and lowercase letters 'i' and software-related terms like 'parsed', 'Mongo', 'Cache', 'Loader', 'implementation', 'Source', and 'class'

    oai_token-act-pair · gpt-3.5-turbo

    references to technical or programming terms

    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
     pudding
    -0.83
     indo
    -0.77
     tug
    -0.76
     seiz
    -0.76
     CONTR
    -0.76
     lim
    -0.76
     ende
    -0.76
    xual
    -0.75
     cher
    -0.75
     occas
    -0.74
    POSITIVE LOGITS
    Abs
    1.62
    Party
    1.60
    Cut
    1.59
    Bl
    1.58
    Int
    1.58
    Power
    1.57
    Min
    1.56
    Empty
    1.56
    Non
    1.56
    Spe
    1.55
    Activations Density 0.160%

    No Known Activations