INDEX

Explanations

proper nouns, specifically names of places, organizations, and people

oai_token-act-pair · gpt-3.5-turbo

proper nouns

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

 ..."

-0.70

[&

-0.63

-0.62

 âĢ¦"

-0.60

.</

-0.60

LAR

-0.58

 thereto

-0.58

 artif

-0.57

natureconservancy

-0.56

..."

-0.53

POSITIVE LOGITS

ogether

0.88

nesty

0.87

withstanding

0.86

jamin

0.86

dinand

0.85

ropolitan

0.83

icularly

0.83

foundland

0.83

odore

0.82

asionally

0.79

Activations Density 0.266%

proper nouns, specifically names of places, organizations, and people

proper nouns

No Comments

No Known Activations