© 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. 9998
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds, especially those with a focus on phosphorylation

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds and their associated terms

    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
     Grande
    -0.78
    HEAD
    -0.76
    MENTS
    -0.72
     Daly
    -0.69
     Siberian
    -0.66
     guiActiveUnfocused
    -0.66
     Heights
    -0.64
    PUT
    -0.63
     caption
    -0.62
     hub
    -0.61
    POSITIVE LOGITS
    okin
    1.32
    ological
    1.28
    ology
    1.27
    opl
    1.24
    ophy
    1.23
    osate
    1.19
    ologic
    1.18
    ogl
    1.17
    onic
    1.15
    ologies
    1.14
    Activations Density 0.049%

    No Known Activations