INDEX

Explanations

statements or arguments being emphasized or highlighted in text

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

õ

-0.45

roh

-0.43

glise

-0.43

Loire

-0.41

braio

-0.41

Portály

-0.41

MatIconModule

-0.40

gida

-0.40

 Crew

-0.40

dè

-0.40

POSITIVE LOGITS

 point

1.32

point

1.31

 POINT

1.29

 Point

1.22

Point

1.20

points

1.19

 points

1.18

POINT

1.14

 POINTS

1.11

 Points

1.08

Activations Density 0.120%

statements or arguments being emphasized or highlighted in text

No Comments

No Known Activations