© 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. 17315
    Prev
    Next
    INDEX
    Explanations

    specific mentions of quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the preposition "in" associated with various contexts

    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
    bos
    -0.72
    ricanes
    -0.67
    entimes
    -0.64
    ãĤ´ãĥ³
    -0.61
     emb
    -0.60
    Interstitial
    -0.59
    zel
    -0.57
     outl
    -0.57
     kidding
    -0.54
    rr
    -0.54
    POSITIVE LOGITS
     existence
    1.22
     circulation
    1.05
     attendance
    1.01
    clusions
    0.99
     contention
    0.98
     succession
    0.89
     jeopardy
    0.85
     sight
    0.84
    operative
    0.83
     question
    0.79
    Activations Density 0.160%

    No Known Activations