INDEX

Explanations

mentions of organizations, positions, and events in news articles

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 knots

-0.72

$$$$

-0.68

 PLEASE

-0.66

achy

-0.66

facing

-0.65

cellaneous

-0.65

LLOW

-0.64

aminer

-0.64

erers

-0.63

anse

-0.63

POSITIVE LOGITS

1.09

1.07

1.05

1.04

1.03

 previous

1.02

Activations Density 4.422%

mentions of organizations, positions, and events in news articles

No Comments

No Known Activations