INDEX

Explanations

phrases related to technological aspects, like programming languages and computer hardware

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 liner

-1.02

LW

-1.01

akery

-0.95

 Starr

-0.90

 Extras

-0.84

ersen

-0.84

 eternity

-0.82

onents

-0.82

Nid

-0.81

 Seah

-0.81

POSITIVE LOGITS

capt

1.14

su

1.13

de

1.10

route

1.10

pour

1.10

cont

1.10

fact

1.09

dist

1.08

equipped

1.06

sung

1.04

Activations Density 0.489%

phrases related to technological aspects, like programming languages and computer hardware

No Comments

No Known Activations