© 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. 4-RES-JB
    11. 510
    Prev
    Next
    INDEX
    Explanations

    phrases related to professional work experience

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "worked for" followed by various durations or contexts

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

    No Comments

    Negative Logits
    clair
    -0.72
    801
    -0.70
    illin
    -0.69
    6000
    -0.68
    7601
    -0.68
    heart
    -0.68
    Balt
    -0.66
    Ire
    -0.65
    oller
    -0.65
    909
    -0.64
    POSITIVE LOGITS
    gotten
    0.97
    geries
    0.92
     hire
    0.91
    bidden
    0.90
     example
    0.89
     instance
    0.85
     awhile
    0.82
    ked
    0.82
    aging
    0.80
    cing
    0.76
    Activations Density 0.217%

    No Known Activations