INDEX

Explanations

terms related to regulations and regulatory environments

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

 sophie

-0.62

 smar

-0.60

 crê

-0.60

 dante

-0.58

 nicolas

-0.58

 impractica

-0.56

 impra

-0.56

 embra

-0.55

 olivia

-0.55

 resis

-0.55

POSITIVE LOGITS

 regulation

1.34

 Regulation

1.24

regulation

1.22

 regulatory

1.18

Regulation

1.17

 regulations

1.14

 regulated

1.14

 regulate

1.13

 regulators

1.13

 regulator

1.13

Activations Density 0.099%

terms related to regulations and regulatory environments

No Comments

No Known Activations