INDEX

Explanations

numerical values

oai_token-act-pair · gpt-3.5-turbo

references to product specifications and measurements

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

 GOODMAN

-0.88

yang

-0.80

ĸļ

-0.75

çīĪ

-0.74

eering

-0.73

gments

-0.72

ezvous

-0.70

 sneaky

-0.68

gie

-0.67

chid

-0.66

POSITIVE LOGITS

 ILCS

1.18

ULT

0.89

ength

0.88

0.82

0.79

0.78

0.77

Â¢

0.77

ishly

0.76

Activations Density 0.027%

numerical values

references to product specifications and measurements

No Comments

No Known Activations