INDEX

Explanations

high-frequency terms or articles in the text

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

thood

-0.83

perse

-0.78

ï¿½ï¿½ï¿½ï¿½

-0.76

ashington

-0.74

leground

-0.73

Scotland

-0.71

minent

-0.70

angering

-0.70

uclear

-0.69

-0.68

POSITIVE LOGITS

 downside

1.30

oret

1.27

 biggest

1.16

 drawback

1.11

 sheer

1.08

 easiest

1.06

 simplest

1.05

 coolest

1.00

 latter

0.99

 cheapest

0.98

Activations Density 0.206%

high-frequency terms or articles in the text

No Comments

No Known Activations