INDEX

Explanations

uncertain statements or estimates

oai_token-act-pair · gpt-3.5-turbo

statements concerning variability and uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.82

é¾įå¥ĳå£«

-0.78

reet

-0.70

ware

-0.67

chwitz

-0.66

ablishment

-0.64

hest

-0.63

Pinterest

-0.62

=~=~

-0.61

 Kiss

-0.61

POSITIVE LOGITS

 vary

1.21

 exceptions

1.07

 differ

1.05

 variations

1.04

 inaccur

1.03

 misinterpret

1.02

 occasionally

1.00

 modifications

0.96

 modify

0.96

 alternatively

0.95

Activations Density 0.446%

uncertain statements or estimates

statements concerning variability and uncertainty

No Comments

No Known Activations