© 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. 2-RES-JB
    11. 12266
    Prev
    Next
    INDEX
    Explanations

    phrases involving dates, locations, and events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distinguishes
    -0.68
    =""
    -0.66
    ographers
    -0.64
    âĢİ
    -0.64
     attaches
    -0.64
    âĢł
    -0.63
    HCR
    -0.62
     anew
    -0.61
     awaits
    -0.61
    ,''
    -0.60
    POSITIVE LOGITS
     same
    1.18
     entirety
    1.09
     latter
    1.08
     guise
    1.01
     aforementioned
    0.97
     midst
    0.97
     aftermath
    0.96
     periphery
    0.94
     simplest
    0.94
     smallest
    0.93
    Activations Density 1.453%

    No Known Activations