INDEX

Explanations

phrases indicating addition or inclusion

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

yah

-0.65

NING

-0.64

Zel

-0.60

ARE

-0.60

zing

-0.59

cdn

-0.58

THR

-0.58

grim

-0.57

mare

-0.57

rior

-0.56

POSITIVE LOGITS

endum

1.32

itional

1.18

ictions

1.14

ition

1.10

itions

1.09

ressing

1.09

itionally

1.07

resses

1.03

ictive

1.03

 insult

1.02

Activations Density 0.543%

phrases indicating addition or inclusion

No Comments

No Known Activations