INDEX

Explanations

phrases related to official statements, actions, or events

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

 unspeak

-0.76

 maneu

-0.69

 FFFF

-0.65

 outlander

-0.64

 impra

-0.63

 ACKNOWLEDGMENTS

-0.63

 snoopy

-0.63

 disagre

-0.61

 vincent

-0.61

 indescri

-0.61

POSITIVE LOGITS

been

0.87

 BEEN

0.79

Been

0.79

 kayo

0.76

 intende

0.76

 been

0.74

 \%$\\

0.65

ISHOP

0.64

 Muhamma

0.64

Faites

0.63

Activations Density 0.207%

phrases related to official statements, actions, or events

No Comments

No Known Activations