INDEX

Explanations

adverbs that modify the degree or frequency of an action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Sod

-0.64

 charging

-0.61

Sod

-0.59

toBe

-0.59

สาย

-0.59

 meda

-0.57

 forgiven

-0.54

 hende

-0.53

 blooming

-0.52

 shaking

-0.52

POSITIVE LOGITS

 have

1.02

verläs

0.97

erdings

0.92

avía

0.89

had

0.89

tonode

0.88

pfung

0.87

NewUrlParser

0.86

did

0.86

 gave

0.86

Activations Density 0.289%

adverbs that modify the degree or frequency of an action

No Comments

No Known Activations