INDEX

Explanations

expressions related to certainty or assurance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "guaranteed" and its variations, indicating certainty or assurance

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

geist

-0.81

insula

-0.77

sonian

-0.76

atics

-0.71

anie

-0.70

arts

-0.70

emouth

-0.70

atic

-0.69

%]

-0.69

bus

-0.68

POSITIVE LOGITS

 guarantee

0.96

 guarantees

0.89

eers

0.88

 validity

0.77

 guaranteeing

0.76

 guarant

0.75

 Guarant

0.71

lessly

0.71

 fulfillment

0.70

 sust

0.68

Activations Density 0.034%

expressions related to certainty or assurance

instances of the word "guaranteed" and its variations, indicating certainty or assurance

No Comments

No Known Activations