INDEX

Explanations

references to scientific terminology or concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

azeera

-0.76

isSpecialOrderable

-0.75

kefeller

-0.73

 proxies

-0.68

escription

-0.67

DeL

-0.66

 appointments

-0.64

 flyers

-0.63

 balloons

-0.62

chwitz

-0.62

POSITIVE LOGITS

ĩ

0.81

thy

0.79

ł

0.78

©

0.77

ĥ

0.77

Ŀ

0.76

phy

0.75

ï¸

0.73

utic

0.73

omical

0.72

Activations Density 0.027%

references to scientific terminology or concepts

No Comments

No Known Activations