INDEX

Explanations

food-related phrases

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PDATE

-0.65

orthern

-0.65

ãĤ¤

-0.64

Ïī

-0.62

cipled

-0.62

lain

-0.62

âķĲâķĲ

-0.62

erity

-0.61

oubted

-0.61

famous

-0.61

POSITIVE LOGITS

 syndrome

1.07

 Syndrome

0.87

(%

0.69

(>

0.68

(<

0.65

atoes

0.64

ilib

0.62

 corpses

0.60

frames

0.59

agram

0.59

Activations Density 0.517%

food-related phrases

No Comments

No Known Activations