INDEX

Explanations

formal terms followed by verbs, actions or situations related to news or events

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

itism

-0.69

ittee

-0.68

ogical

-0.68

00200000

-0.68

 Chocobo

-0.67

velength

-0.67

ican

-0.65

iless

-0.64

oka

-0.62

izes

-0.62

POSITIVE LOGITS

neck

1.07

fast

0.92

away

0.84

waters

0.83

bow

0.79

down

0.75

 apart

0.72

downs

0.72

water

0.72

hearted

0.71

Activations Density 4.749%

formal terms followed by verbs, actions or situations related to news or events

No Comments

No Known Activations