INDEX

Explanations

words related to actions or events

oai_token-act-pair · gpt-3.5-turbo

words related to measurements or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

×ŀ

-0.61

CHAR

-0.60

ECD

-0.60

URRENT

-0.59

 democratic

-0.59

ãĥ£

-0.58

 chrome

-0.58

 saline

-0.57

dem

-0.57

 birth

-0.57

POSITIVE LOGITS

uggest

1.11

etter

1.10

hower

1.09

etting

1.02

hip

1.02

hooting

1.01

leeve

1.00

ettings

0.97

oft

0.96

poons

0.94

Activations Density 0.064%

words related to actions or events

words related to measurements or evaluations

No Comments

No Known Activations