© 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. 11-RES-JB
    11. 10116
    Prev
    Next
    INDEX
    Explanations

    words related to pathways or courses of action

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various paths or pathways in relation to broader concepts or directions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sting
    -0.62
    orporated
    -0.62
     sterling
    -0.61
     contrace
    -0.61
    rongh
    -0.58
     Quant
    -0.57
    iling
    -0.56
    Sum
    -0.56
     Marketable
    -0.56
     awoken
    -0.56
    POSITIVE LOGITS
    finding
    1.38
    ogen
    1.31
    finder
    1.31
    ologies
    1.27
    ophys
    1.17
    ologist
    1.13
    ogenesis
    1.12
    find
    1.07
    ways
    1.01
     forward
    0.99
    Activations Density 0.060%

    No Known Activations