INDEX

Explanations

special characters and non-English alphabets with a specific emphasis on the character 'ë' and specific combinations like 'ïķ'

oai_token-act-pair · gpt-3.5-turbo

specific characters or glyphs used in a non-standard encoding or script

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.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

wagen

-0.83

romeda

-0.72

theless

-0.71

ablishment

-0.71

bourg

-0.70

ambers

-0.69

lander

-0.67

 Feet

-0.67

peed

-0.66

oleon

-0.65

POSITIVE LOGITS

¹

1.08

ª

0.96

º

0.95

ī

0.95

¨

0.93

Ĩ

0.93

ķ

0.91

¦

0.91

Į

0.87

Ģ

0.87

Activations Density 0.029%

special characters and non-English alphabets with a specific emphasis on the character 'ë' and specific combinations like 'ïķ'

specific characters or glyphs used in a non-standard encoding or script

No Comments

No Known Activations