INDEX

Explanations

arrows mentioned in scientific contexts

oai_token-act-pair · gpt-3.5-turbo

specific visual elements and colors related to diagrams or illustrations

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

answered

-0.74

compl

-0.69

©¶æ¥µ

-0.68

Ultimately

-0.65

itutional

-0.65

 incest

-0.64

discrimination

-0.64

Eventually

-0.64

 Furious

-0.63

antic

-0.63

POSITIVE LOGITS

 depicts

1.09

below

1.03

 illustration

1.01

 screenshot

1.00

 Figure

0.99

Figure

0.98

 screenshots

0.96

 pict

0.95

 Sketch

0.95

 illust

0.91

Activations Density 0.323%

arrows mentioned in scientific contexts

specific visual elements and colors related to diagrams or illustrations

No Comments

No Known Activations