© 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. 8-RES-JB
    11. 17092
    Prev
    Next
    INDEX
    Explanations

    words that have the prefix "un-"

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "un" indicating negation or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsolved
    -0.76
     unexplained
    -0.74
     halves
    -0.72
     Away
    -0.67
     rendition
    -0.66
     divergence
    -0.65
     crossover
    -0.64
     widening
    -0.63
     4096
    -0.62
     smaller
    -0.61
    POSITIVE LOGITS
    apolog
    1.07
    balanced
    1.05
    plug
    1.03
    rave
    1.02
    responsive
    1.01
    idad
    1.00
    offic
    0.99
    ruly
    0.98
    prof
    0.97
    imp
    0.97
    Activations Density 0.029%

    No Known Activations