INDEX

Explanations

phrases indicating uncertainty or conflict in opinions

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

gage

-0.50

Pool

-0.48

Hut

-0.47

Gap

-0.47

 Mecca

-0.47

skinned

-0.46

uration

-0.46

Zac

-0.45

gat

-0.45

 queues

-0.45

POSITIVE LOGITS

 thereafter

1.02

 thereto

0.75

 thereof

0.74

 afterward

0.72

etheless

0.71

sequent

0.71

 subsequent

0.70

 alike

0.70

catentry

0.69

 myself

0.67

Activations Density 0.492%

phrases indicating uncertainty or conflict in opinions

No Comments

No Known Activations