© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22325
    Prev
    Next
    INDEX
    Explanations

    mentions of attempts or efforts to create or build something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "something" 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
    DOS
    -0.80
    ude
    -0.69
    ardi
    -0.68
    inders
    -0.66
    de
    -0.66
    ilt
    -0.66
    anos
    -0.65
    ortex
    -0.65
    phones
    -0.65
    ildo
    -0.64
    POSITIVE LOGITS
     else
    1.50
    Else
    1.35
     resembling
    1.16
     akin
    0.97
     intangible
    0.95
     Else
    0.90
     miraculous
    0.89
     tangible
    0.88
     unheard
    0.88
    iverse
    0.88
    Activations Density 0.080%

    No Known Activations