INDEX

Explanations

specific locations or events

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

Dist

-0.70

âĨĳ

-0.69

dds

-0.68

Definition

-0.67

imilation

-0.65

ographers

-0.63

amount

-0.62

ynt

-0.61

_{

-0.61

saf

-0.60

POSITIVE LOGITS

 behalf

1.52

 Wednesday

1.17

 Thursday

1.16

 Tuesday

1.14

 Monday

1.11

 Tues

1.08

 Capitol

1.07

 Friday

1.06

etime

1.06

 Saturday

1.06

Activations Density 0.107%

specific locations or events

No Comments

No Known Activations