INDEX

Explanations

prepositions like "in" that indicate location or position

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

 Donation

-0.75

 SHARES

-0.68

 empath

-0.67

ange

-0.65

 disgusted

-0.63

onica

-0.58

 toughness

-0.57

 dishonest

-0.56

 happiest

-0.55

aturday

-0.55

POSITIVE LOGITS

drawn

0.96

accessible

0.90

ked

0.87

 fruition

0.86

 moth

0.85

activated

0.84

escap

0.84

 circulation

0.82

urated

0.82

jected

0.82

Activations Density 0.177%

prepositions like "in" that indicate location or position

No Comments

No Known Activations