INDEX

Explanations

names following a particular pattern in the dataset

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

<bos>

-0.84

ArrowToggle

-0.71

 kaynağından

-0.67

MessageTagHelper

-0.67

 gynhyrchwyd

-0.67

formik

-0.65

AndEndTag

-0.65

ItemBackground

-0.64

 Paglinawan

-0.63

parsedMessage

-0.61

POSITIVE LOGITS

 emphat

1.90

 increa

1.88

 maneu

1.87

 reluct

1.86

 depic

1.85

 inev

1.81

 disagre

1.78

 encomp

1.77

 affor

1.75

 apprehen

1.74

Activations Density 0.493%

names following a particular pattern in the dataset

No Comments

No Known Activations