INDEX

Explanations

elements and characteristics related to ancient medical theories, particularly the four humors

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

nir

-0.97

kun

-0.90

bush

-0.90

iband

-0.90

conservancy

-0.88

wald

-0.88

nesday

-0.86

nown

-0.85

hov

-0.84

onz

-0.83

POSITIVE LOGITS

 Description

1.04

Avg

1.01

 Average

1.01

 Category

0.99

 Name

0.97

 Actual

0.96

 Amount

0.95

 Value

0.92

 Notes

0.92

 Difference

0.92

Activations Density 10.359%

elements and characteristics related to ancient medical theories, particularly the four humors

No Comments

No Known Activations