INDEX

Explanations

phrases related to physical movement and actions

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

 Unreal

-0.70

Nex

-0.65

 Prevention

-0.64

 deficiencies

-0.61

history

-0.60

Ins

-0.60

fail

-0.59

BDS

-0.59

haven

-0.59

Els

-0.58

POSITIVE LOGITS

 gazed

1.04

 approached

0.98

 walked

0.96

 exited

0.95

 unfolded

0.94

 waited

0.94

 awaited

0.93

 stared

0.90

 stood

0.89

 paced

0.89

Activations Density 0.080%

phrases related to physical movement and actions

No Comments

No Known Activations