INDEX

Explanations

instances of doubt or uncertainty in statements

oai_token-act-pair · gpt-3.5-turbo

expressions of reasons and justifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 occupations

-0.87

arest

-0.84

ancial

-0.77

 ageing

-0.77

quartered

-0.76

negie

-0.75

 laboratories

-0.75

 dwellings

-0.75

entary

-0.73

emporary

-0.72

POSITIVE LOGITS

he

1.36

 Rollins

1.00

 Harbaugh

0.98

He

0.98

she

0.96

 pissed

0.95

his

0.95

him

0.94

He

0.94

 Saban

0.93

Activations Density 0.955%

instances of doubt or uncertainty in statements

expressions of reasons and justifications

No Comments

No Known Activations