INDEX

Explanations

mentions of the word "hop"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 payable

-0.73

ateral

-0.67

 confir

-0.58

ISE

-0.57

 conclud

-0.57

Downloadha

-0.57

 bundled

-0.56

 withd

-0.56

 reconc

-0.56

$$$$

-0.56

POSITIVE LOGITS

eful

1.10

Hop

1.06

efully

0.93

lite

0.90

Hop

0.84

retty

0.82

hop

0.80

sticks

0.78

hop

0.78

along

0.78

Activations Density 8.008%

mentions of the word "hop"

No Comments

No Known Activations