INDEX

Explanations

mentions of persons or organizations in news articles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "In" and the structure of formal statements or reports

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

 hands

-0.71

 favour

-0.67

 favor

-0.66

 Ghostbusters

-0.66

 scrap

-0.65

 flatt

-0.65

 endeav

-0.65

 detract

-0.65

 priorit

-0.64

 fors

-0.64

POSITIVE LOGITS

Born

1.11

Together

0.93

ccording

0.91

Contribut

0.87

Writing

0.85

Educ

0.84

Coach

0.84

Lake

0.84

Joined

0.84

Cover

0.83

Activations Density 0.485%

mentions of persons or organizations in news articles

occurrences of the word "In" and the structure of formal statements or reports

No Comments

No Known Activations