INDEX

Explanations

explicit indicators of certainty or emphasis

oai_token-act-pair · gpt-3.5-turbo

the word "clearly" and its context in sentences

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

rella

-0.90

eport

-0.74

 lightly

-0.72

ERY

-0.69

aily

-0.69

tackle

-0.68

regate

-0.66

ntil

-0.65

illi

-0.65

ertodd

-0.65

POSITIVE LOGITS

 deline

1.21

 marked

1.00

 identifiable

0.97

 defined

0.96

 differentiated

0.95

 stated

0.90

 labelled

0.90

 distinguish

0.88

 communicated

0.87

 articulated

0.87

Activations Density 0.053%

explicit indicators of certainty or emphasis

the word "clearly" and its context in sentences

No Comments

No Known Activations