© 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. 9980
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming languages

    oai_token-act-pair · gpt-3.5-turbo

    programming constructs related to paths and indices in data structures

    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
    etsk
    -0.79
    aucuses
    -0.76
    accompan
    -0.75
    oshenko
    -0.75
    kefeller
    -0.74
     arrang
    -0.72
     inaccur
    -0.72
    ovember
    -0.71
     lobb
    -0.71
     endings
    -0.70
    POSITIVE LOGITS
     String
    1.40
     Integer
    1.37
     Boolean
    1.31
     bool
    1.25
     Int
    1.24
     Float
    1.21
     Option
    1.16
    String
    1.14
     Array
    1.14
    uint
    1.12
    Activations Density 0.071%

    No Known Activations