INDEX

Explanations

terms related to the legitimacy and effects of government practices and policies

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

 apprehen

-1.09

 reluct

-1.06

 inev

-1.04

 accla

-1.03

 intersper

-1.03

 depic

-0.97

 emphat

-0.96

 embra

-0.93

 encomp

-0.93

 sophistic

-0.93

POSITIVE LOGITS

emplar

0.62

ercice

0.60

gruntled

0.57

 ajuns

0.57

 disambiguazione

0.57

 trecut

0.56

 Meksiku

0.56

 declarat

0.56

nor

0.54

 AssemblyTitle

0.54

Activations Density 0.612%

terms related to the legitimacy and effects of government practices and policies

No Comments

No Known Activations