INDEX

Explanations

instances of words related to vision or appearance characteristics like eye color, hair, or design in a technical context

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icum

-0.79

 ACPI

-0.68

theless

-0.66

 Bundy

-0.64

lishes

-0.64

Else

-0.64

minus

-0.64

vik

-0.64

cha

-0.63

channelAvailability

-0.63

POSITIVE LOGITS

 sockets

1.16

ight

0.90

 socket

0.88

 lobe

0.88

bones

0.85

beam

0.85

 brow

0.84

eye

0.83

ewitness

0.82

holes

0.80

Activations Density 0.023%

instances of words related to vision or appearance characteristics like eye color, hair, or design in a technical context

No Comments

No Known Activations