INDEX

Explanations

text related to online interactions or technology

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

WHERE

-0.68

enance

-0.68

 Norn

-0.67

 ..............

-0.62

BILITIES

-0.62

bers

-0.61

Known

-0.59

lished

-0.58

lings

-0.58

Freedom

-0.57

POSITIVE LOGITS

auts

1.14

nen

1.14

autical

1.12

nect

1.11

nette

1.11

ucle

1.08

ews

1.06

cÃ©

1.05

ique

1.03

neau

1.01

Activations Density 0.806%

text related to online interactions or technology

No Comments

No Known Activations