© 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. 17590
    Prev
    Next
    INDEX
    Explanations

    instances where a specified number of items are being referred to

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or sets of items

    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
    Spoiler
    -0.72
    za
    -0.68
     Cosponsors
    -0.65
    ALLY
    -0.64
    virt
    -0.63
     Parables
    -0.62
    only
    -0.62
    gg
    -0.61
    imate
    -0.61
     srfAttach
    -0.61
    POSITIVE LOGITS
     consisted
    0.71
     resulted
    0.68
     involves
    0.68
     involved
    0.68
     contained
    0.65
     originated
    0.65
     corresponds
    0.64
     referred
    0.63
     consists
    0.63
     occurs
    0.62
    Activations Density 0.075%

    No Known Activations