© 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. 8207
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences or emotions, particularly expressing thoughts or actions

    oai_token-act-pair · gpt-3.5-turbo
    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
     comprising
    -0.54
     purportedly
    -0.52
    eligible
    -0.51
     reportedly
    -0.48
    arthy
    -0.48
     governed
    -0.46
     respectively
    -0.46
     annually
    -0.45
     Manufact
    -0.45
     jointly
    -0.45
    POSITIVE LOGITS
     fucking
    0.66
     fuckin
    0.64
    laughs
    0.63
     shitty
    0.61
     crazy
    0.61
     crappy
    0.59
     fucked
    0.59
     silly
    0.58
     messed
    0.57
     stupid
    0.57
    Activations Density 5.108%

    No Known Activations