INDEX

Explanations

credit-related terms, particularly focusing on words related to financial transactions and settlements

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

 fatis

-0.52

 Molière

-0.50

ambiental

-0.47

 Gertrude

-0.45

 fupp

-0.45

 fhort

-0.45

SafeAreaView

-0.45

 sympy

-0.45

 obfer

-0.45

 Fallon

-0.44

POSITIVE LOGITS

 credit

1.42

credit

1.36

 Credit

1.29

Credit

1.26

 CREDIT

1.24

 credits

1.17

credits

1.10

 Credits

1.09

CREDIT

1.05

Credits

0.98

Activations Density 0.068%

credit-related terms, particularly focusing on words related to financial transactions and settlements

No Comments

No Known Activations