INDEX

Explanations

short descriptive phrases at the end of captions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Caption" within various contexts

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

abol

-0.82

axis

-0.79

nesia

-0.72

bye

-0.71

bers

-0.69

neg

-0.69

omsky

-0.68

kn

-0.68

ught

-0.67

rugged

-0.67

POSITIVE LOGITS

 Caption

1.25

 Thumbnails

1.02

 Close

1.00

 largeDownload

0.92

 Shutdown

0.86

 Scenes

0.84

 Loading

0.84

 Gallery

0.81

 Highlights

0.81

Thumbnail

0.81

Activations Density 0.010%

short descriptive phrases at the end of captions

occurrences of the word "Caption" within various contexts

No Comments

No Known Activations