INDEX

Explanations

phrases related to maturity or development

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of "mat" or related variations in context

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

éĹĺ

-0.92

ngth

-0.83

FUL

-0.72

vous

-0.69

IGHTS

-0.68

 Mouth

-0.64

Ô

-0.62

HOME

-0.61

OFF

-0.61

æĸ¹

-0.61

POSITIVE LOGITS

hematically

1.48

rices

1.34

urity

1.13

ially

1.02

rice

1.01

het

0.98

uring

0.98

rics

0.97

rim

0.95

ril

0.93

Activations Density 0.007%

phrases related to maturity or development

repeated mentions of "mat" or related variations in context

No Comments

No Known Activations