INDEX

Explanations

phrases related to physical objects like tools and weapon names

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 alkoh

-1.13

 kram

-1.07

lü

-1.06

 kras

-1.03

 maksi

-1.01

uhr

-1.00

 panik

-1.00

 minimalis

-0.98

 augus

-0.96

hek

-0.96

POSITIVE LOGITS

 wielded

0.67

 resultList

0.66

 OBSERVATIONS

0.62

 ryzen

0.61

 resultMap

0.61

 earnestness

0.59

 holdt

0.59

 sticks

0.58

 APPARATUS

0.58

 itemList

0.58

Activations Density 0.302%

phrases related to physical objects like tools and weapon names

No Comments

No Known Activations