INDEX

Explanations

words related to historical wars, military actions, and armed conflicts

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

OGR

-0.80

ITY

-0.71

obook

-0.70

Asset

-0.69

*/(

-0.68

 snipp

-0.61

 metab

-0.61

KE

-0.61

 answ

-0.61

ITIES

-0.60

POSITIVE LOGITS

II

1.00

lords

0.99

lord

0.96

III

0.93

ombat

0.83

planes

0.82

bler

0.81

riors

0.80

rior

0.78

XVI

0.76

Activations Density 0.015%

words related to historical wars, military actions, and armed conflicts

No Comments

No Known Activations