INDEX

Explanations

instances of the phrase "don't" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Samar

-0.64

 Tasman

-0.62

 Axel

-0.62

BMC

-0.61

 partName

-0.60

 Samson

-0.59

NH

-0.58

RAF

-0.58

Override

-0.58

 Lowell

-0.57

POSITIVE LOGITS

ember

0.91

ufact

0.79

iversary

0.77

udes

0.77

addafi

0.76

tarian

0.75

aughter

0.74

resent

0.73

imately

0.73

tal

0.73

Activations Density 0.248%

instances of the phrase "don't" in various contexts

No Comments

No Known Activations