INDEX

Explanations

phrases related to comparison or evaluation

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

 newList

-0.71

 newArr

-0.64

 confided

-0.60

 luxuriant

-0.59

 indoc

-0.56

 Rodrig

-0.56

 Bartholo

-0.56

 intersper

-0.55

 forbade

-0.55

 newData

-0.55

POSITIVE LOGITS

terms

0.87

 terms

0.84

Terms

0.82

TERMS

0.79

 TERMS

0.78

 Terms

0.73

 termes

0.60

 himo

0.58

homonymie

0.57

 regards

0.55

Activations Density 0.048%

phrases related to comparison or evaluation

No Comments

No Known Activations