INDEX

Explanations

occurrences of specific phrases or sequences of words

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

 imageName

-0.56

 userModel

-0.55

iterranean

-0.53

 resultList

-0.52

 signUp

-0.49

 virtù

-0.48

 kommit

-0.47

 userEmail

-0.47

resents

-0.47

 newArr

-0.47

POSITIVE LOGITS

/**

0.63

 Last

0.62

Last

0.60

 last

0.59

 LAST

0.57

 stopp

0.56

awtextra

0.54

last

0.52

setLast

0.52

 vertik

0.51

Activations Density 0.180%

occurrences of specific phrases or sequences of words

No Comments

No Known Activations