INDEX

Explanations

mentions of the publication "Business Insider"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific media outlets, particularly Business Insider and its associated platforms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 lifes

-0.73

liam

-0.72

 stret

-0.63

ometric

-0.62

igmat

-0.61

 strengths

-0.61

 knit

-0.60

gone

-0.60

ardless

-0.60

 curric

-0.60

POSITIVE LOGITS

 Insight

0.83

 Investigative

0.83

OPLE

0.79

Leaks

0.78

 Digest

0.77

 Insider

0.74

 Syndicate

0.72

EEK

0.72

Phoenix

0.72

 Weekly

0.71

Activations Density 0.182%

mentions of the publication "Business Insider"

mentions of specific media outlets, particularly Business Insider and its associated platforms

No Comments

No Known Activations