© 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. 3-RES-JB
    11. 11970
    Prev
    Next
    INDEX
    Explanations

    references to executive positions in a business or production context

    oai_token-act-pair · gpt-3.5-turbo

    the term "executive" and its various related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reincarn
    -0.80
    apo
    -0.77
    Els
    -0.75
    Downloadha
    -0.75
    ERO
    -0.71
    cale
    -0.71
    COMPLE
    -0.69
    Prev
    -0.68
    ulia
    -0.67
    osate
    -0.67
    POSITIVE LOGITS
    utive
    1.02
     executive
    0.92
     director
    0.90
     officer
    0.83
     chef
    0.83
     chairman
    0.82
     summary
    0.81
     branch
    0.81
    director
    0.79
    TAIN
    0.78
    Activations Density 0.012%

    No Known Activations