INDEX

Explanations

phrases related to image credits

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

houses

-0.75

hang

-0.73

stones

-0.69

halla

-0.68

hall

-0.68

ring

-0.67

Ļ½

-0.66

 hook

-0.65

amba

-0.65

 binge

-0.64

POSITIVE LOGITS

 Actions

0.82

ï

0.72

 IMAGES

0.72

 VIDEOS

0.72

enes

0.71

thumbnails

0.71

 EDIT

0.69

 Reporter

0.69

 Shots

0.69

 PLoS

0.68

Activations Density 0.050%

phrases related to image credits

punctuation marks, specifically parentheses

No Comments

No Known Activations