INDEX

Explanations

terms related to the code's finalization and declaration keywords

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.74

 himſelf

-0.70

 Cæsar

-0.70

 Babyl

-0.66

 Jefus

-0.66

 ſche

-0.64

ObjectModel

-0.63

 itſelf

-0.63

 elders

-0.62

 Issus

-0.61

POSITIVE LOGITS

 final

1.82

final

1.34

 finally

0.98

finally

0.86

最终

0.76

 Finally

0.73

 FINAL

0.70

Finally

0.70

FINAL

0.69

Final

0.64

Activations Density 0.072%

terms related to the code's finalization and declaration keywords

No Comments

No Known Activations