INDEX

Explanations

phrases descriptive of features and evaluations in reviews, especially related to video games

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

ivi

-1.59

 emphat

-1.54

 accla

-1.49

 volunte

-1.43

 increa

-1.41

 embra

-1.41

 apprehen

-1.41

 philanth

-1.40

 reluct

-1.39

 Confe

-1.39

POSITIVE LOGITS

 regarding

0.62

spli

0.61

 when

0.60

 towards

0.59

 toward

0.59

CONFLICT

0.58

in

0.58

for

0.58

 among

0.57

 between

0.57

Activations Density 0.407%

phrases descriptive of features and evaluations in reviews, especially related to video games

No Comments

No Known Activations