© 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. 1-RES-JB
    11. 16293
    Prev
    Next
    INDEX
    Explanations

    events or instances of someone leaving or departing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "departure."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verbs
    -0.80
    ohyd
    -0.77
    ells
    -0.72
    ollo
    -0.66
     reservoirs
    -0.63
    hed
    -0.63
    organic
    -0.63
    ums
    -0.62
    ized
    -0.61
     reservoir
    -0.59
    POSITIVE LOGITS
     departure
    1.19
     departures
    0.93
     depart
    0.83
    ffen
    0.68
     anytime
    0.66
    >[
    0.64
     undermin
    0.63
     departing
    0.63
    otomy
    0.63
    rez
    0.62
    Activations Density 0.007%

    No Known Activations