INDEX

Explanations

phrases or discussions related to food and recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

ļéĨĴ

-0.77

][

-0.70

istar

-0.70

 Originally

-0.69

terday

-0.69

responsible

-0.68

arious

-0.65

incial

-0.62

uper

-0.61

Iraq

-0.61

POSITIVE LOGITS

 reap

1.18

 enjoy

1.16

 preferably

1.04

 beware

1.03

 congr

1.00

 bask

1.00

 then

0.98

 yourself

0.97

 THEN

0.95

cknow

0.95

Activations Density 0.115%

phrases or discussions related to food and recipes

No Comments

No Known Activations