INDEX

Explanations

mentions of hair-related terms like "hair salon," "salon," and descriptions of hair

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

 bascul

-0.51

 ché

-0.51

Dawg

-0.51

 Pockets

-0.50

 cushi

-0.48

mnop

-0.48

 Stretcher

-0.47

 Assorted

-0.47

Ferdin

-0.47

 Wrench

-0.46

POSITIVE LOGITS

 hair

1.41

Hair

1.32

hair

1.29

 Hair

1.29

 HAIR

1.23

HAIR

1.08

 hairs

1.00

haired

0.99

 haired

0.92

hairs

0.87

Activations Density 0.078%

mentions of hair-related terms like "hair salon," "salon," and descriptions of hair

No Comments

No Known Activations