© 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. 10796
    Prev
    Next
    INDEX
    Explanations

    names or terms that start with "Ne"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific topic or entity

    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
     injection
    -0.69
    inately
    -0.67
    hips
    -0.66
    loo
    -0.65
     dissolved
    -0.65
     illegally
    -0.62
     sidx
    -0.62
     accounting
    -0.62
    DOWN
    -0.59
     bearer
    -0.59
    POSITIVE LOGITS
    arest
    1.36
    umann
    1.29
    braska
    1.24
    verend
    1.20
    olithic
    1.19
    uron
    1.11
    utral
    1.11
    oliberal
    1.11
    arthed
    1.04
    utra
    1.04
    Activations Density 0.013%

    No Known Activations