INDEX

Explanations

proper nouns related to specific locations or entities

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

ãĥĦ

-0.84

 guiActiveUnfocused

-0.77

ãĥĥãĥĪ

-0.75

wagen

-0.71

 Nanto

-0.68

 Bombay

-0.65

 Tinder

-0.64

 compuls

-0.62

 Belg

-0.61

jamin

-0.60

POSITIVE LOGITS

entric

1.01

ilia

0.93

colo

0.89

ada

0.83

otte

0.83

aught

0.82

otine

0.82

adas

0.82

cone

0.79

ivil

0.78

Activations Density 0.005%

proper nouns related to specific locations or entities

No Comments

No Known Activations