INDEX

Explanations

references to short content

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ILLE

-0.82

IRO

-0.70

ONSORED

-0.69

ADRA

-0.69

ICAN

-0.65

itational

-0.65

GAN

-0.65

ITAL

-0.64

CLASSIFIED

-0.64

Magikarp

-0.63

POSITIVE LOGITS

sighted

1.21

ening

1.17

comings

1.13

falls

1.08

lived

1.07

ened

1.02

ener

0.98

changed

0.95

cuts

0.94

coming

0.94

Activations Density 0.408%

references to short content

No Comments

No Known Activations