INDEX

Explanations

phrases that indicate a result or outcome

oai_token-act-pair · gpt-3.5-turbo

inquiries or statements focused on results or conclusions

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

inventoryQuantity

-0.89

igraph

-0.85

 Offense

-0.67

terday

-0.66

addons

-0.65

osponsors

-0.65

yi

-0.64

 Topic

-0.63

Limit

-0.63

 Antiqu

-0.62

POSITIVE LOGITS

 disastrous

0.69

 abundantly

0.68

 astounding

0.68

 predictably

0.67

 reprodu

0.64

 spectacular

0.63

ãĥĢ

0.62

 priceless

0.62

 hilarious

0.61

 devastating

0.61

Activations Density 0.159%

phrases that indicate a result or outcome

inquiries or statements focused on results or conclusions

No Comments

No Known Activations