INDEX

Explanations

graphic or programming-related terms, specifically those related to file extensions and suffixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 المعيارى

-0.90

 للمعارف

-0.83

 useCallback

-0.81

BeginContext

-0.81

httphttps

-0.80

 newOwner

-0.79

MemoryWarning

-0.77

AxisAlignment

-0.77

RectangleBorder

-0.76

}`).

-0.74

POSITIVE LOGITS

 suffix

0.71

suffix

0.66

Suffix

0.60

 appended

0.55

 suffixes

0.50

ffix

0.46

SUFFIX

0.44

artifactId

0.44

缀

0.42

 derechos

0.42

Activations Density 0.274%

graphic or programming-related terms, specifically those related to file extensions and suffixes

No Comments

No Known Activations