INDEX

Explanations

elements associated with numerical data or statistics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Amer

-0.68

 Occupations

-0.68

 Jesuit

-0.65

ami

-0.65

agents

-0.64

 Mech

-0.63

abases

-0.63

 Caucas

-0.63

 vocabulary

-0.62

rices

-0.62

POSITIVE LOGITS

destroy

1.08

 withdrawn

0.97

 Cancel

0.96

 cance

0.95

redo

0.90

ancel

0.90

 withdraw

0.89

Destroy

0.89

 canceled

0.88

 abst

0.88

Activations Density 0.246%

elements associated with numerical data or statistics

No Comments

No Known Activations