INDEX

Explanations

phrases indicating the act of searching for something or someone

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

PerformLayout

-0.50

Referințe

-0.49

Vegeu

-0.48

Bibliografie

-0.48

Dès

-0.46

Chaque

-0.46

Legături

-0.46

 kompatibel

-0.46

Rifer

-0.46

Пі

-0.46

POSITIVE LOGITS

 LOOKING

0.98

 looking

0.86

 tranquillo

0.84

looking

0.76

 lookin

0.75

fto

0.73

 Looking

0.72

LOOKING

0.71

 dispen

0.70

 tramont

0.68

Activations Density 0.097%

phrases indicating the act of searching for something or someone

No Comments

No Known Activations