INDEX

Explanations

references to game-related terms and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.63

-0.58

webElementXpaths

-0.57

-0.51

vw

-0.47

𝘄

-0.45

wch

-0.45

wv

-0.45

wdata

-0.44

POSITIVE LOGITS

We

0.71

 Will

0.61

 Were

0.61

 Willing

0.60

 Window

0.60

 Went

0.59

 Well

0.59

You

0.59

 Wide

0.58

We

0.57

Activations Density 0.796%

references to game-related terms and programming constructs

No Comments

No Known Activations