INDEX

Explanations

phrases related to legality or legal issues

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

resa

-0.35

 Originally

-0.34

apeake

-0.31

ribune

-0.30

odore

-0.28

 Latest

-0.28

Newsletter

-0.28

hillary

-0.28

gor

-0.27

itars

-0.27

POSITIVE LOGITS

]."

0.63

)).

0.60

.).

0.58

}.

0.55

]).

0.52

%.

0.52

`.

0.51

.ï¿½

0.51

'."

0.50

.''.

0.50

Activations Density 17.177%

phrases related to legality or legal issues

No Comments

No Known Activations