INDEX

Explanations

Japanese names and terms associated with people and characters

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

pit

-0.58

 highly

-0.55

 help

-0.55

 venons

-0.55

 near

-0.54

man

-0.54

 year

-0.54

 life

-0.53

 sainte

-0.53

身

-0.52

POSITIVE LOGITS

 يتيمه

1.10

+#+

0.90

ThroughAttribute

0.86

GOTREF

0.81

Билгалдахарш

0.79

 חיצוניים

0.79

 FetchType

0.78

DoubleQuotes

0.78

LEncoder

0.78

حوالہ

0.77

Activations Density 0.059%

Japanese names and terms associated with people and characters

No Comments

No Known Activations