© 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. 3-RES-JB
    11. 10644
    Prev
    Next
    INDEX
    Explanations

    non-alphabet characters (for example, punctuation marks) in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating confusion or uncertainty in conversations

    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
    hement
    -0.88
     orchestr
    -0.77
     internationally
    -0.75
     pegged
    -0.71
     bundled
    -0.70
     untouched
    -0.70
    chnology
    -0.70
    uly
    -0.69
     centrally
    -0.69
     ousted
    -0.69
    POSITIVE LOGITS
    Advertisements
    0.97
    Trivia
    0.97
    CONCLUS
    0.94
    ³³³³³³³³³³³³³³³³
    0.93
    ³³³³
    0.92
    --------------------------------------------------------
    0.92
    Anyway
    0.92
    ################################
    0.91
    ................................................................
    0.90
    Chapter
    0.90
    Activations Density 0.810%

    No Known Activations