INDEX

Explanations

phrases indicating possession or self-reference

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

MLLoader

-1.21

Datuak

-1.07

^(@)

-1.03

NUMX

-0.97

 насељу

-0.96

kháu

-0.95

 ſind

-0.94

клопе

-0.91

 "..\..\

-0.91

Хьажоргаш

-0.91

POSITIVE LOGITS

0.66

0.61

’

0.60

↵

0.55

bu

0.53

and

0.53

The

0.53

0.52

Activations Density 1.564%

phrases indicating possession or self-reference

No Comments

No Known Activations