INDEX

Explanations

functions and methods related to user data manipulation and processing

oai_token-act-pair · gpt-3.5-turbo

technical terms and references related to programming and data management

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Britann

-0.70

aida

-0.65

 societies

-0.65

 folklore

-0.64

APTER

-0.63

ĸļ

-0.63

 aided

-0.62

çĶ°

-0.61

 challeng

-0.60

Tec

-0.60

POSITIVE LOGITS

()

0.97

().

0.83

miss

0.81

():

0.79

Second

0.77

wordpress

0.77

Limit

0.76

Result

0.75

Process

0.75

Activations Density 0.122%

functions and methods related to user data manipulation and processing

technical terms and references related to programming and data management

No Comments

No Known Activations