© 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. 9031
    Prev
    Next
    INDEX
    Explanations

    words related to business operations and strategies

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to business operations and organizational structures

    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
     oneself
    -0.83
    otropic
    -0.77
    icable
    -0.68
    cair
    -0.67
    ometric
    -0.66
    ocent
    -0.65
    hurst
    -0.63
    illian
    -0.59
    astical
    -0.58
    depending
    -0.58
    POSITIVE LOGITS
     counterparts
    0.97
     counterpart
    0.87
     woes
    0.87
     portfolio
    0.84
     predecessors
    0.82
     brethren
    0.81
    mates
    0.81
     repertoire
    0.81
     regimen
    0.81
     arsenal
    0.79
    Activations Density 0.443%

    No Known Activations