INDEX

Explanations

names or proper nouns

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-1.22

archiviato

-0.70

GIH

-0.70

 oprot

-0.63

makeText

-0.61

湖

-0.61

 ffilmiau

-0.61

map

-0.60

jdbc

-0.60

 Mike

-0.60

POSITIVE LOGITS

 🤣🤣

1.58

ftu

1.49

 hairc

1.48

 milf

1.47

 ecru

1.45

 maneu

1.40

 affor

1.36

 ftre

1.35

 eiffel

1.33

fta

1.33

Activations Density 1.011%

names or proper nouns

No Comments

No Known Activations