INDEX

Explanations

words related to immobility or motionlessness

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

¶ħ

-0.95

ģĸ

-0.78

 lawy

-0.77

bys

-0.73

rists

-0.73

BY

-0.72

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.67

 Warfare

-0.67

 strip

-0.65

\\\\\\\\

-0.65

POSITIVE LOGITS

igrants

1.38

aterial

1.32

igrant

1.30

igrated

1.30

agine

1.30

igration

1.30

ersion

1.25

ovable

1.25

igr

1.19

obile

1.18

Activations Density 0.016%

words related to immobility or motionlessness

No Comments

No Known Activations