INDEX

Explanations

phrases related to historical or technical information

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

no

-0.56

far

-0.54

 hints

-0.51

 spare

-0.50

 most

-0.49

stdbool

-0.48

organize

-0.48

 Compare

-0.48

POSITIVE LOGITS

 lapto

1.25

 silikon

1.23

 reger

1.22

 dises

1.17

cyr

1.16

 kafe

1.14

 etui

1.13

fordable

1.13

 soggior

1.11

 ciga

1.11

Activations Density 0.053%

phrases related to historical or technical information

No Comments

No Known Activations