INDEX

Explanations

words related to health, medicine, and well-being

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

 Brill

-0.74

ANG

-0.63

 Murd

-0.61

 Page

-0.61

 Quantity

-0.61

ilibrium

-0.59

 Frames

-0.59

 Swing

-0.59

 Sail

-0.58

 Mansion

-0.58

POSITIVE LOGITS

merga

1.19

ocy

0.89

ofer

0.79

opers

0.77

bara

0.74

cies

0.73

ongyang

0.72

otin

0.72

ggle

0.72

ococ

0.72

Activations Density 0.016%

words related to health, medicine, and well-being

No Comments

No Known Activations