© 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. 3647
    Prev
    Next
    INDEX
    Explanations

    phrases related to projects and initiatives

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to partnerships, projects, or collaborative initiatives

    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
    etheless
    -0.73
    ritic
    -0.70
    awed
    -0.68
    istered
    -0.67
    asionally
    -0.66
    addafi
    -0.66
    gettable
    -0.64
    eas
    -0.64
    Sometimes
    -0.59
    lean
    -0.58
    POSITIVE LOGITS
     comprises
    1.42
     aims
    1.41
     consists
    1.39
     will
    1.36
     involves
    1.36
     includes
    1.36
     intends
    1.31
     entails
    1.29
     encompasses
    1.26
     coincides
    1.25
    Activations Density 0.394%

    No Known Activations