INDEX

Explanations

information related to biology, evolution, and research in scientific fields

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

estate

-0.86

 kneeling

-0.79

 hating

-0.76

TRUMP

-0.76

 whine

-0.75

 haircut

-0.74

iquette

-0.73

 hates

-0.73

 cursing

-0.72

 lockout

-0.72

POSITIVE LOGITS

 researchers

1.53

Researchers

1.41

 scientists

1.38

 neuroscience

1.36

 Researchers

1.35

 study

1.33

 computational

1.32

Abstract

1.29

 experiments

1.29

Study

1.29

Activations Density 4.040%

information related to biology, evolution, and research in scientific fields

No Comments

No Known Activations