© 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. 12838
    Prev
    Next
    INDEX
    Explanations

    musical terms related to compositions or pieces

    oai_token-act-pair · gpt-3.5-turbo

    financial and logistical details related to costs and expenses

    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
    ãĥķãĤ©
    -0.82
    Crash
    -0.80
    Voice
    -0.76
    ensical
    -0.75
    Attempts
    -0.75
    Wik
    -0.71
    Enlarge
    -0.69
    Developer
    -0.69
    é¾įåĸļ士
    -0.69
    Clar
    -0.68
    POSITIVE LOGITS
     TBA
    0.93
     either
    0.84
     both
    0.80
     etc
    0.76
     unspecified
    0.74
     each
    0.73
     respectively
    0.73
     duration
    0.72
     whichever
    0.71
     block
    0.71
    Activations Density 0.199%

    No Known Activations