INDEX

Explanations

phrases indicating excessiveness or extreme qualities

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

 Архів

-0.66

 kual

-0.63

-0.62

Datuak

-0.61

tableFuture

-0.61

 navbar

-0.56

 Giordano

-0.56

 carreras

-0.56

DebuggerStep

-0.56

җ

-0.56

POSITIVE LOGITS

Too

1.04

Too

0.99

TOO

0.90

TOO

0.88

too

0.86

too

0.82

 excessive

0.82

 Excessive

0.81

 exces

0.81

Excessive

0.80

Activations Density 0.235%

phrases indicating excessiveness or extreme qualities

No Comments

No Known Activations