INDEX

Explanations

phrases related to power and authority

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

<bos>

-0.69

 adel

-0.50

 незавершена

-0.50

 avent

-0.48

mir

-0.48

glBind

-0.45

 espar

-0.43

gado

-0.43

 comod

-0.43

المناصب

-0.43

POSITIVE LOGITS

 force

1.15

force

1.06

 Force

1.05

 forces

1.00

 FORCE

1.00

Force

0.98

forces

0.96

Forces

0.96

 Forces

0.94

FORCE

0.92

Activations Density 0.087%

phrases related to power and authority

No Comments

No Known Activations