INDEX

Explanations

terms related to design and media, particularly in the context of fashion and literature

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

setVerticalGroup

-0.57

 ſur

-0.57

 виправивши

-0.56

};*/

-0.55

 cauſe

-0.54

 ſta

-0.51

 uſed

-0.50

 purpoſe

-0.50

 ſtand

-0.49

IsContent

-0.49

POSITIVE LOGITS

 junk

0.79

 Junk

0.78

holic

0.75

Junk

0.74

junk

0.72

 addict

0.70

erati

0.69

 buff

0.69

 fanatic

0.68

thusi

0.67

Activations Density 0.289%

terms related to design and media, particularly in the context of fashion and literature

No Comments

No Known Activations