INDEX

Explanations

uncertainty or lack of clarity in statements

oai_token-act-pair · gpt-3.5-turbo

expressions of uncertainty or ambiguity

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nov

-0.67

Zone

-0.65

Exper

-0.63

bern

-0.62

Minor

-0.61

../

-0.60

nova

-0.60

INT

-0.58

 throats

-0.57

upiter

-0.57

POSITIVE LOGITS

 whether

1.38

why

1.19

how

1.16

whether

1.04

 exactly

1.01

WHY

0.93

why

0.93

HOW

0.88

if

0.87

 Whether

0.85

Activations Density 0.058%

uncertainty or lack of clarity in statements

expressions of uncertainty or ambiguity

No Comments

No Known Activations