INDEX

Explanations

phrases expressing confidence in the ability to accomplish something

oai_token-act-pair · gpt-3.5-turbo

phrases expressing capability or potential

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

furt

-0.76

teen

-0.66

 Falling

-0.64

estate

-0.64

-0.62

 Cheong

-0.60

pend

-0.58

num

-0.58

ele

-0.58

 Shooting

-0.58

POSITIVE LOGITS

't

1.20

 afford

1.19

 safely

1.12

 feas

1.02

 improve

0.95

 replicate

0.93

 overcome

0.92

 withstand

0.92

NOT

0.92

 revive

0.88

Activations Density 0.200%

phrases expressing confidence in the ability to accomplish something

phrases expressing capability or potential

No Comments

No Known Activations