INDEX

Explanations

instances of the name "Sam"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Sam."

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

 fences

-0.73

CLASSIFIED

-0.67

inventoryQuantity

-0.66

 Dame

-0.65

 scheduling

-0.64

cffff

-0.63

çĶŁ

-0.62

 tribunal

-0.62

err

-0.62

 trolling

-0.60

POSITIVE LOGITS

pling

1.25

ples

1.19

urai

1.16

pler

1.11

oan

1.08

uel

1.07

achine

1.00

mons

0.95

mar

0.94

atar

0.94

Activations Density 0.011%

instances of the name "Sam"

mentions of the name "Sam."

No Comments

No Known Activations