INDEX

Explanations

phrases related to criticism or negative assessment

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

 Whence

-0.70

ypeł

-0.66

 peppa

-0.65

Şi

-0.63

alnız

-0.62

 withal

-0.61

 shenan

-0.61

 hairc

-0.60

 Mémoires

-0.60

 madonna

-0.58

POSITIVE LOGITS

 reputa

0.55

 grans

0.54

SourceChecksum

0.51

hoj

0.50

dè

0.50

 palet

0.49

Ukra

0.49

Gilla

0.49

AsUp

0.48

逅

0.48

Activations Density 0.289%

phrases related to criticism or negative assessment

No Comments

No Known Activations