INDEX

Explanations

numbers or percentages related to changes or trends

oai_token-act-pair · gpt-3.5-turbo

phrases indicating changes quantified by percentage

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

ational

-0.73

 largeDownload

-0.73

ivia

-0.72

 succeeded

-0.70

finished

-0.69

itialized

-0.68

meat

-0.68

 succeeds

-0.67

aughtered

-0.64

ruby

-0.64

POSITIVE LOGITS

 virtue

1.04

0.83

 leaps

0.80

products

0.79

 fiat

0.77

0.76

 multiplying

0.75

 eliminating

0.68

0.67

Activations Density 0.087%

numbers or percentages related to changes or trends

phrases indicating changes quantified by percentage

No Comments

No Known Activations