© 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. 7872
    Prev
    Next
    INDEX
    Explanations

    corporations, organizations, and locations

    oai_token-act-pair · gpt-3.5-turbo

    names of companies, brands, and notable entities

    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
    soType
    -0.65
    depending
    -0.63
    TAG
    -0.61
    tnc
    -0.59
    etimes
    -0.56
    Materials
    -0.56
    duc
    -0.54
     Grateful
    -0.54
    %%%%
    -0.53
    "],"
    -0.53
    POSITIVE LOGITS
     fared
    1.20
     dominates
    1.20
     likewise
    1.14
     meanwhile
    1.10
     has
    1.06
     famously
    1.06
     seems
    1.02
     tends
    1.01
     occupies
    1.01
     lacks
    0.99
    Activations Density 0.614%

    No Known Activations