INDEX

Explanations

references to failure or lack of success

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

onen

-0.78

dar

-0.77

utra

-0.75

enfranch

-0.75

iser

-0.75

ript

-0.74

inda

-0.73

arya

-0.72

onto

-0.72

atu

-0.72

POSITIVE LOGITS

 miser

1.68

lect

1.03

 horribly

1.03

 dism

1.02

 catast

1.00

ingly

0.93

fully

0.89

 spectacular

0.85

DEV

0.85

nces

0.84

Activations Density 7.681%

references to failure or lack of success

No Comments

No Known Activations