© 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. 10-RES-JB
    11. 12890
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons, motivations, and justifications

    oai_token-act-pair · gpt-3.5-turbo

    references to specific events or entities related to releases, studies, or surveys

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cowork
    -0.56
    AppData
    -0.55
     annexed
    -0.55
    Joined
    -0.54
    phies
    -0.52
     consecut
    -0.51
    ById
    -0.50
    姫
    -0.50
     playable
    -0.49
    uthor
    -0.48
    POSITIVE LOGITS
     varies
    1.39
     depends
    1.38
     differs
    1.26
     lies
    1.20
     revolves
    1.15
     involves
    1.15
     is
    1.12
     rests
    1.11
     derives
    1.11
     consists
    1.06
    Activations Density 0.293%

    No Known Activations