INDEX

Explanations

capital letters in sequences

oai_token-act-pair · gpt-3.5-turbo

letters or symbols that may represent significant categories or entities 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 @ 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

 pony

-0.81

 blah

-0.76

 ðŁĻĤ

-0.74

 Strip

-0.73

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.73

EStream

-0.73

 Joker

-0.71

Magikarp

-0.70

ĸļ

-0.70

 Cerberus

-0.69

POSITIVE LOGITS

ogether

1.20

resa

1.13

roximately

1.12

earing

1.07

ounding

1.07

alling

1.04

aring

1.00

ensions

1.00

itting

0.97

etting

0.97

Activations Density 0.259%

capital letters in sequences

letters or symbols that may represent significant categories or entities in various contexts

No Comments

No Known Activations