© 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. 8-RES-JB
    11. 7652
    Prev
    Next
    INDEX
    Explanations

    names ending in 'is' and 'aki' and the word 'Mickey'

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥ŀ
    -0.76
    è¦ļéĨĴ
    -0.74
     stakes
    -0.66
     thumbnail
    -0.63
    ruciating
    -0.61
     galleries
    -0.57
     oats
    -0.56
    ishers
    -0.56
    theless
    -0.54
     Pages
    -0.53
    POSITIVE LOGITS
    abeth
    1.34
    terness
    1.06
    earch
    1.03
    peed
    1.01
    ection
    0.99
    aurus
    0.98
    rael
    0.97
    henko
    0.96
    TRY
    0.95
    olation
    0.93
    Activations Density 0.061%

    No Known Activations