INDEX

Explanations

occurrences of the word "Had"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Had" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

CLS

-0.72

ç«

-0.67

ä½¿

-0.64

å¥³

-0.63

ugu

-0.62

Ú

-0.62

advertisement

-0.62

 DISTRICT

-0.61

CRIP

-0.60

ocol

-0.60

POSITIVE LOGITS

rons

0.96

 Been

0.90

luck

0.84

 been

0.83

ewitness

0.83

 undergone

0.81

gotten

0.80

ibur

0.80

been

0.78

 gotten

0.78

Activations Density 0.012%

occurrences of the word "Had"

instances of the word "Had" in various contexts

No Comments

No Known Activations