INDEX

Explanations

words related to coincidences or the concept of two or more events occurring by chance

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

severe

-0.85

emouth

-0.83

bern

-0.82

erer

-0.80

verb

-0.78

erers

-0.74

aina

-0.73

Services

-0.72

ikan

-0.71

heit

-0.70

POSITIVE LOGITS

 coincidence

1.19

 coinc

1.16

identally

1.10

idental

1.07

idences

0.85

 coincide

0.84

istically

0.79

 twin

0.78

 coincided

0.77

 occurrences

0.74

Activations Density 0.047%

words related to coincidences or the concept of two or more events occurring by chance

No Comments

No Known Activations