INDEX

Explanations

comparisons between different entities or concepts based on qualities or characteristics

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

Published

-0.74

hiba

-0.68

 VIDEOS

-0.64

 destro

-0.63

idates

-0.60

endiary

-0.60

ulty

-0.59

icals

-0.59

 Accessed

-0.58

icators

-0.57

POSITIVE LOGITS

liest

1.65

lier

1.53

lihood

1.44

liness

1.13

 minded

0.98

minded

0.91

able

0.90

 unto

0.75

 ours

0.70

inking

0.69

Activations Density 0.037%

comparisons between different entities or concepts based on qualities or characteristics

No Comments

No Known Activations