INDEX

Explanations

words related to the eye and visual perception in a technical or descriptive context

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

channelAvailability

-1.23

_-

-1.14

minus

-1.04

icum

-1.02

ivari

-1.00

tons

-0.99

lishes

-0.98

 congr

-0.98

Else

-0.97

ities

-0.96

POSITIVE LOGITS

 sockets

1.66

 socket

1.28

ewitness

1.20

obe

1.18

eye

1.17

 lobe

1.15

eyed

1.13

ight

1.13

bones

1.11

 nose

1.08

Activations Density 0.818%

words related to the eye and visual perception in a technical or descriptive context

No Comments

No Known Activations