INDEX

Explanations

phrases related to food and cooking, as well as criticism or judgmental language

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.33

 vainly

-1.50

 impelled

-1.23

 intersper

-1.14

 apprehen

-1.13

 endeavouring

-1.04

 ineffec

-1.02

 endeavored

-1.01

 triumphantly

-1.00

 hastened

-1.00

POSITIVE LOGITS

 sappi

1.28

eronau

1.25

capulco

1.22

 ristor

1.21

dirond

1.15

 monaster

1.15

 tramont

1.15

quarelle

1.13

 soggior

1.12

 pecuni

1.11

Activations Density 0.907%

phrases related to food and cooking, as well as criticism or judgmental language

No Comments

No Known Activations