INDEX

Explanations

scientific and medical terms related to biology and research

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Kara

-0.61

ASA

-0.57

 blot

-0.57

INT

-0.56

 Alley

-0.56

Rew

-0.56

 ILCS

-0.56

AAA

-0.55

Ã©n

-0.55

 Anaheim

-0.54

POSITIVE LOGITS

 underscores

1.19

 depends

1.10

 illustrates

1.07

 hinges

1.06

 coincided

1.06

 coincides

1.06

 suggests

1.06

 reinforces

1.05

 implies

1.05

 outwe

1.05

Activations Density 0.722%

scientific and medical terms related to biology and research

No Comments

No Known Activations