INDEX

Explanations

company relationships, specifically highlighting sister companies and affiliates

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yers

-0.71

inen

-0.69

bugs

-0.67

imar

-0.64

wn

-0.64

someone

-0.64

idential

-0.63

blind

-0.62

tics

-0.62

frey

-0.61

POSITIVE LOGITS

heses

0.96

hesis

0.93

 entity

0.88

 sister

0.84

 Chapters

0.79

hetical

0.76

 acronym

0.75

 sibling

0.73

 competitor

0.66

 successor

0.64

Activations Density 0.091%

company relationships, specifically highlighting sister companies and affiliates

No Comments

No Known Activations