INDEX

Explanations

phrases indicating instruction or guidance

oai_token-act-pair · gpt-3.5-turbo

the phrase "by" followed by numerical values or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

SPONSORED

-0.73

TB

-0.68

ETF

-0.65

 pains

-0.63

upon

-0.62

als

-0.62

 "$:/

-0.60

Silver

-0.59

inea

-0.59

itives

-0.59

POSITIVE LOGITS

 virtue

1.27

products

1.05

laws

0.94

 default

0.93

catch

0.93

gone

0.90

product

0.89

 clicking

0.84

 multiplying

0.84

 means

0.82

Activations Density 0.156%

phrases indicating instruction or guidance

the phrase "by" followed by numerical values or actions

No Comments

No Known Activations