INDEX

Explanations

inconsistencies or contradictions in written text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Rumble

-0.77

ocene

-0.66

 Stockholm

-0.61

 bang

-0.61

 Dota

-0.59

 Ventura

-0.58

stay

-0.57

 genuinely

-0.56

ELY

-0.54

GET

-0.54

POSITIVE LOGITS

forward

0.81

 situated

0.80

 inclined

0.79

quartered

0.77

 minded

0.76

apy

0.74

etheless

0.73

tainment

0.72

leep

0.72

nown

0.70

Activations Density 0.024%

inconsistencies or contradictions in written text

No Comments

No Known Activations