© 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. 2767
    Prev
    Next
    INDEX
    Explanations

    the word "cont" or "Cont" within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cont" 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
    lihood
    -0.80
    EStream
    -0.80
    manship
    -0.72
    ãĤ¬
    -0.71
    ï¸
    -0.68
    STER
    -0.68
    OPLE
    -0.66
    ħĭ
    -0.63
     scratch
    -0.62
     Lans
    -0.60
    POSITIVE LOGITS
    ributed
    1.41
    roversial
    1.39
    ribution
    1.32
    rovers
    1.29
    ainment
    1.28
    ainers
    1.25
    ribute
    1.22
    emporary
    1.21
    rast
    1.18
    ribut
    1.17
    Activations Density 0.034%

    No Known Activations