INDEX

Explanations

mentions of news publications

oai_token-act-pair · gpt-3.5-turbo

references to media outlets or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

soDeliveryDate

-0.77

range

-0.75

interstitial

-0.75

orate

-0.73

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.68

actionDate

-0.68

nants

-0.67

bryce

-0.66

nexus

-0.65

alties

-0.65

POSITIVE LOGITS

 reported

1.31

 understands

1.24

 reports

1.20

 investigates

1.20

ran

1.15

 reporter

1.14

 inquired

1.14

 speculated

1.08

 publishes

1.08

 contacted

1.07

Activations Density 0.231%

mentions of news publications

references to media outlets or publications

No Comments

No Known Activations