INDEX

Explanations

measurements and units related to weight, length, and temperature

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

bred

-0.65

 resent

-0.59

 disple

-0.58

icent

-0.56

rology

-0.56

leased

-0.56

venge

-0.56

 Palace

-0.54

 fledgling

-0.54

amac

-0.53

POSITIVE LOGITS

 apiece

1.25

 increments

1.16

bsp

0.91

abyte

0.84

 teasp

0.81

per

0.80

ABV

0.75

cake

0.73

 Radius

0.72

Ī

0.71

Activations Density 0.105%

measurements and units related to weight, length, and temperature

No Comments

No Known Activations