INDEX

Explanations

numeric information related to seasons and episodes in a television series

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

Đối

-0.67

Máy

-0.67

istoitu

-0.65

Causas

-0.64

Ưu

-0.64

Còn

-0.64

Bảo

-0.64

máy

-0.64

Objetivos

-0.63

Hiện

-0.63

POSITIVE LOGITS

 impra

2.03

 increa

1.95

 depic

1.92

 maneu

1.91

 encomp

1.88

 disagre

1.88

 inappro

1.84

 reluct

1.83

 inev

1.80

 excru

1.76

Activations Density 0.152%

numeric information related to seasons and episodes in a television series

No Comments

No Known Activations