INDEX

Explanations

scientific terms and concepts

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

 Yanuk

-0.65

âĢ¢âĢ¢

-0.62

 Shades

-0.61

atra

-0.61

eper

-0.61

 Gamb

-0.59

 timers

-0.59

terior

-0.58

teen

-0.58

 Tactics

-0.57

POSITIVE LOGITS

 fiction

0.99

 Fiction

0.94

sonian

0.93

 scientist

0.91

 labs

0.91

 physicist

0.89

icist

0.86

Research

0.84

 research

0.84

 researcher

0.83

Activations Density 0.702%

scientific terms and concepts

No Comments

No Known Activations