© 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. 3091
    Prev
    Next
    INDEX
    Explanations

    phrases indicating limitation or finality

    oai_token-act-pair · gpt-3.5-turbo

    the word "only" and its variations related to limitations or scarcity

    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
    insula
    -0.74
    align
    -0.68
    axis
    -0.64
     anytime
    -0.64
     includ
    -0.63
    essler
    -0.62
     belie
    -0.61
    finder
    -0.61
    ahead
    -0.60
    stem
    -0.60
    POSITIVE LOGITS
     marginally
    0.91
     LIMITED
    0.79
     superficial
    0.78
     scratched
    0.76
     limited
    0.74
     ONE
    0.74
    Ń·
    0.72
     sporadic
    0.72
     minor
    0.72
     minimal
    0.71
    Activations Density 0.073%

    No Known Activations