INDEX

Explanations

proper nouns, specifically the name "Donald Trump"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Donald Trump."

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

 guiActiveUnfocused

-0.68

Completed

-0.66

Member

-0.64

 forth

-0.64

 urgency

-0.63

nexus

-0.63

 mater

-0.63

Graphics

-0.62

 Angels

-0.61

MQ

-0.61

POSITIVE LOGITS

 Trump

1.22

son

1.12

 Donald

1.00

 Glover

0.94

trump

0.91

Trump

0.88

 Sterling

0.85

Donald

0.85

 Judd

0.83

 Duck

0.82

Activations Density 0.030%

proper nouns, specifically the name "Donald Trump"

references to the name "Donald Trump."

No Comments

No Known Activations