INDEX

Explanations

quotes from various sources

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

 GEAR

-0.75

 gearing

-0.67

INGTON

-0.66

etheless

-0.61

 reinforcement

-0.60

 contacting

-0.57

 fixture

-0.57

 firsthand

-0.57

 yarn

-0.57

 internationally

-0.57

POSITIVE LOGITS

lling

1.19

cks

1.15

arer

1.13

lder

1.13

ldon

1.12

pherd

1.12

gemony

1.07

arers

1.07

ALTH

1.06

aton

1.05

Activations Density 0.608%

quotes from various sources

No Comments

No Known Activations