INDEX

Explanations

verbs related to expressing opinions or observations

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

 nece

-0.98

fte

-0.92

 effe

-0.90

mef

-0.89

 lein

-0.84

 acce

-0.83

 perfon

-0.83

fto

-0.83

fta

-0.82

 ille

-0.81

POSITIVE LOGITS

GEBURTSDATUM

0.73

 guangdong

0.59

say

0.57

say

0.56

entious

0.55

ertion

0.55

OGND

0.55

 autorytatywna

0.55

idated

0.52

 mußte

0.52

Activations Density 0.187%

verbs related to expressing opinions or observations

No Comments

No Known Activations