INDEX

Explanations

references to various entities and their relationships in specific contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

poken

-0.53

بوابة

-0.51

 rumah

-0.42

 rues

-0.42

MUL

-0.42

azzle

-0.42

 Rücks

-0.41

 irmãos

-0.40

シマ

-0.40

ányi

-0.40

POSITIVE LOGITS

 صوتيه

0.80

ⓧ

0.77

 تضيفلها

0.77

раздо

0.71

Efq

0.68

awtextra

0.67

findpost

0.67

 greateſt

0.66

}{*}{}

0.62

 raiſ

0.62

Activations Density 1.096%

references to various entities and their relationships in specific contexts

No Comments

No Known Activations