INDEX

Explanations

instances of the word "said."

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

selves

-0.73

Pont

-0.70

negie

-0.69

hetically

-0.64

gettable

-0.63

ï¸

-0.63

isol

-0.63

ãĥ¼ãĥĨ

-0.63

ogether

-0.62

 arrang

-0.62

POSITIVE LOGITS

 goodbye

0.83

 hello

0.81

 Offline

0.74

bye

0.73

BST

0.69

 âĨĳ

0.66

ago

0.64

 Vampire

0.63

 Posts

0.63

estamp

0.63

Activations Density 0.043%

instances of the word "said."

No Comments

No Known Activations