INDEX

Explanations

important phrases or specific names in a text

oai_token-act-pair · gpt-3.5-turbo

metrics related to performance and status in various contexts

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

 Berks

-0.84

æ©

-0.81

cob

-0.81

 thous

-0.79

 beet

-0.78

john

-0.78

 Nanto

-0.77

 bart

-0.73

 Quadro

-0.73

bats

-0.73

POSITIVE LOGITS

 stability

1.04

ability

1.03

atibility

1.03

 accuracy

1.02

 pathology

1.02

 modesty

1.01

 integrity

1.01

ency

1.00

 mitigation

1.00

 severity

0.98

Activations Density 0.226%

important phrases or specific names in a text

metrics related to performance and status in various contexts

No Comments

No Known Activations