© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 5080
    Prev
    Next
    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    specific dates or numerical references

    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
    cientious
    -0.63
    ensical
    -0.60
     behavi
    -0.59
     tremend
    -0.58
    angible
    -0.58
     proport
    -0.58
    withstanding
    -0.57
     Provided
    -0.57
     ancest
    -0.55
    osponsors
    -0.54
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.77
    ember
    0.72
     Memorial
    0.68
    th
    0.64
     onwards
    0.63
     onward
    0.61
     mids
    0.61
     anniversary
    0.57
     Shen
    0.57
    ths
    0.57
    Activations Density 0.075%

    No Known Activations