© 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. 1467
    Prev
    Next
    INDEX
    Explanations

    instances of the word "opening"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "opening."

    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
    cia
    -0.88
    lust
    -0.67
    tics
    -0.65
    ortium
    -0.65
    ka
    -0.65
    zin
    -0.65
    GO
    -0.64
    Math
    -0.64
    met
    -0.62
    ford
    -0.61
    POSITIVE LOGITS
     Doors
    0.94
     doors
    0.91
     opening
    0.89
     curtains
    0.80
     parentheses
    0.79
     openings
    0.79
    opening
    0.78
     reopen
    0.77
     ceremonies
    0.76
     opener
    0.74
    Activations Density 0.012%

    No Known Activations