INDEX

Explanations

references to specific locations or places

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

illary

-0.69

UE

-0.65

ãĥ¼ãĥĨãĤ£

-0.62

arium

-0.62

uum

-0.61

ORY

-0.61

KE

-0.60

UES

-0.58

ãĤº

-0.58

 Distribut

-0.57

POSITIVE LOGITS

hang

1.22

drive

1.14

tones

1.14

priced

1.09

lord

1.07

haul

1.06

grown

1.06

loading

1.05

reaching

1.04

whelming

1.03

Activations Density 0.330%

references to specific locations or places

No Comments

No Known Activations