INDEX

Explanations

terms related to cooking techniques, ingredients, and instructions

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

ships

-0.78

âĸ¬âĸ¬

-0.77

SPONSORED

-0.75

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.74

Spons

-0.70

forcing

-0.69

PRO

-0.69

VERTIS

-0.68

accompanied

-0.66

ORED

-0.66

POSITIVE LOGITS

 chop

1.19

 onions

1.01

 chopping

0.96

sticks

0.96

 Chop

0.95

 onion

0.95

aneous

0.95

 slices

0.92

 garlic

0.91

 roast

0.89

Activations Density 0.026%

terms related to cooking techniques, ingredients, and instructions

No Comments

No Known Activations