INDEX

Explanations

words related to a specific language alphabet or script

oai_token-act-pair · gpt-3.5-turbo

non-English characters or symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Flavoring

-0.70

iasco

-0.69

 Collider

-0.69

 partName

-0.68

=-=-=-=-

-0.67

 Circus

-0.65

ãĥ¼ãĥĨ

-0.63

olphins

-0.62

 Conversation

-0.61

 Contest

-0.61

POSITIVE LOGITS

Î»

0.91

ÑĢ

0.85

çĶ°

0.85

¼

0.84

Ðµ

0.78

cffffcc

0.77

Ð

0.77

Ñģ

0.75

¦

0.75

Ð´

0.73

Activations Density 0.146%

words related to a specific language alphabet or script

non-English characters or symbols

No Comments

No Known Activations