INDEX

Explanations

proper nouns and technical terms related to science and technology

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

ãĥ¼ãĥĨãĤ£

-0.85

olicy

-0.75

 sterling

-0.74

ãģį

-0.74

 Chaser

-0.69

 Tycoon

-0.68

ãģĭ

-0.67

ãģ¯

-0.66

åĳ

-0.66

å£

-0.65

POSITIVE LOGITS

manac

1.29

gebra

1.20

umni

1.19

gorithm

1.14

ibaba

1.14

ameda

1.12

 Jazeera

1.10

gorith

1.10

aska

1.09

oha

1.09

Activations Density 0.888%

proper nouns and technical terms related to science and technology

No Comments

No Known Activations