© 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. 24464
    Prev
    Next
    INDEX
    Explanations

    keywords related to switches or settings

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and complex sentence 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
    ":"/
    -0.81
    acas
    -0.71
     guiActiveUn
    -0.69
    Enlarge
    -0.69
    ãĥ¤
    -0.68
    ãĤ¡
    -0.65
    abouts
    -0.64
    Ħ¢
    -0.62
    ISE
    -0.61
    Original
    -0.61
    POSITIVE LOGITS
     whereas
    1.89
     while
    1.88
     whilst
    1.74
    while
    1.62
     followed
    1.47
     respectively
    1.09
     although
    1.03
     flanked
    0.99
     meanwhile
    0.98
     but
    0.94
    Activations Density 0.556%

    No Known Activations