INDEX

Explanations

phrases that provide clarity or insight into complex subjects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

참고

-0.58

 kaynağından

-0.56

 समीक्षक

-0.55

 Official

-0.54

LookAnd

-0.54

eseorang

-0.52

IContainer

-0.52

AddTagHelper

-0.51

withId

-0.51

 createSlice

-0.51

POSITIVE LOGITS

 about

1.09

how

1.02

why

0.97

 siitä

0.88

 what

0.79

 tentang

0.74

 explaining

0.71

about

0.70

why

0.69

 regarding

0.68

Activations Density 0.453%

phrases that provide clarity or insight into complex subjects

No Comments

No Known Activations