INDEX

Explanations

phrases indicating quoted speech or reported statements

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the reporting or stating of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

twitch

-0.68

æĸ

-0.63

ä½ľ

-0.62

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.62

ãĥĩ

-0.61

spread

-0.60

 Talent

-0.60

ivot

-0.59

è¯

-0.57

sv

-0.57

POSITIVE LOGITS

:"

0.77

 "...

0.75

 omin

0.67

 "âĢ¦

0.66

 authors

0.65

"(

0.64

:-

0.61

 quoting

0.60

lishes

0.59

:'

0.59

Activations Density 0.199%

phrases indicating quoted speech or reported statements

phrases that indicate the reporting or stating of information

No Comments

No Known Activations