INDEX

Explanations

instructions or step-by-step procedures for performing a task

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Cash

-0.82

ictions

-0.73

nesty

-0.73

HCR

-0.73

BIL

-0.72

arians

-0.70

mart

-0.69

aneers

-0.67

Malley

-0.67

obia

-0.67

POSITIVE LOGITS

 periphery

1.19

 vicinity

1.07

 ceiling

1.06

 smallest

1.05

 aforementioned

1.03

 slightest

1.01

 latter

1.00

 same

0.99

 lowest

0.97

 upper

0.96

Activations Density 11.598%

instructions or step-by-step procedures for performing a task

No Comments

No Known Activations