INDEX

Explanations

items or resources offered as additional content or information in a variety of contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "more" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

xtap

-0.79

-0.71

OCK

-0.70

ader

-0.69

ress

-0.68

 Reconstruction

-0.68

Enlarge

-0.68

atan

-0.67

 Zimmer

-0.64

itudes

-0.63

POSITIVE LOGITS

 than

1.13

 info

0.98

 detailed

0.93

 importantly

0.91

 stringent

0.91

 expensive

0.91

 sophisticated

0.90

 complicated

0.88

 efficient

0.88

 elaborate

0.86

Activations Density 0.145%

items or resources offered as additional content or information in a variety of contexts

instances of the word "more" in various contexts

No Comments

No Known Activations