© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7103
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions occurring

    oai_token-act-pair · gpt-3.5-turbo

    ending punctuation marks, specifically periods, indicating the end of statements

    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
    riet
    -0.75
    ande
    -0.72
    utsch
    -0.70
    anguage
    -0.69
    untarily
    -0.68
    uly
    -0.67
     autonom
    -0.67
    ptin
    -0.66
     dich
    -0.66
     censored
    -0.64
    POSITIVE LOGITS
     Additionally
    1.02
     Regardless
    0.97
     Obviously
    0.96
     Those
    0.96
     Luckily
    0.94
     But
    0.94
     That
    0.93
     However
    0.92
     Fortunately
    0.92
     Unfortunately
    0.91
    Activations Density 0.575%

    No Known Activations