INDEX

Explanations

instances of the word "nod"

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

inventoryQuantity

-0.84

 Tycoon

-0.69

 Hebdo

-0.68

Ļ½

-0.66

Cov

-0.66

 tabl

-0.66

ãĥ¯ãĥ³

-0.64

utherland

-0.62

=#

-0.61

cens

-0.60

POSITIVE LOGITS

atory

1.03

nod

1.02

ules

1.00

ule

0.88

irection

0.87

emonic

0.86

 toward

0.84

 approving

0.83

vironment

0.83

endum

0.83

Activations Density 0.030%

instances of the word "nod"

No Comments

No Known Activations