INDEX

Explanations

mentions of the American people

oai_token-act-pair · gpt-3.5-turbo

references to the "American people."

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

inventoryQuantity

-0.84

catentry

-0.84

Smith

-0.70

Prev

-0.69

TAG

-0.69

à¸

-0.67

Reloaded

-0.65

 promotional

-0.65

SET

-0.64

tein

-0.64

POSITIVE LOGITS

folk

0.83

ocracy

0.80

hood

0.78

 electing

0.75

 uprising

0.75

 elected

0.72

orate

0.72

 harmed

0.68

 entrusted

0.68

orsi

0.67

Activations Density 0.043%

mentions of the American people

references to the "American people."

No Comments

No Known Activations