INDEX

Explanations

terms related to equipment, items, products, and their characteristics

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

 Sons

-0.76

 Winds

-0.73

noon

-0.71

©¶æ

-0.70

keye

-0.68

Ã±o

-0.64

egal

-0.63

nee

-0.63

beck

-0.62

Robin

-0.62

POSITIVE LOGITS

ivity

0.86

ively

0.77

uria

0.75

ivities

0.75

 vendors

0.74

 supplier

0.73

 offerings

0.73

 purchases

0.72

store

0.72

 suppliers

0.72

Activations Density 2.595%

terms related to equipment, items, products, and their characteristics

No Comments

No Known Activations