INDEX

Explanations

proper nouns and phrases referring to specific events or people

oai_token-act-pair · gpt-3.5-turbo

shocking or surprising events or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

etheless

-0.56

uitive

-0.51

ciplinary

-0.50

imposed

-0.45

ometimes

-0.44

 ï¿½

-0.43

 ACTIONS

-0.42

prisingly

-0.42

upon

-0.41

lees

-0.41

POSITIVE LOGITS

"]

1.22

")

1.22

.")

1.18

").

1.17

%"

1.15

"—

1.12

"),

1.11

";

1.08

",

1.07

"?

1.06

Activations Density 0.977%

proper nouns and phrases referring to specific events or people

shocking or surprising events or descriptions

No Comments

No Known Activations