INDEX

Explanations

phrases related to social interactions, behaviors, and potential red flags in a humorous tone

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pamph

-0.62

bcryptjs

-0.59

allclose

-0.57

 corrom

-0.56

símbolo

-0.55

xxv

-0.55

§.

-0.54

árbol

-0.54

"}")

-0.53

 unwarran

-0.53

POSITIVE LOGITS

 unless

1.10

unless

0.99

 anymore

0.96

 except

0.83

nor

0.79

 whatsoever

0.78

 anything

0.77

except

0.73

anything

0.73

 Unless

0.72

Activations Density 0.592%

phrases related to social interactions, behaviors, and potential red flags in a humorous tone

No Comments

No Known Activations