© 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. 11-RES-JB
    11. 23942
    Prev
    Next
    INDEX
    Explanations

    elements of code involving summing or aggregating collections

    oai_token-act-pair · gpt-3.5-turbo

    code structures and operations related to arrays and collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milton
    -0.89
     Tec
    -0.84
     Dame
    -0.82
     Alic
    -0.81
    ppa
    -0.79
    enance
    -0.79
     Hubbard
    -0.78
    tek
    -0.77
     Official
    -0.75
     MIS
    -0.74
    POSITIVE LOGITS
     iterator
    1.44
     iter
    1.40
     arrays
    1.31
     tuple
    1.30
    Iterator
    1.27
     sorted
    1.22
    Iter
    1.22
     collections
    1.19
     array
    1.17
    Array
    1.16
    Activations Density 0.223%

    No Known Activations