INDEX

Explanations

references to specific dates or historical events

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

.''

-0.55

-0.54

 without

-0.52

.</

-0.52

âĢł

-0.50

 with

-0.49

SPONSORED

-0.48

."

-0.48

.-

-0.48

leeve

-0.48

POSITIVE LOGITS

 same

0.96

 latter

0.96

 aforementioned

0.95

 slightest

0.91

 entirety

0.90

 smallest

0.88

 entire

0.88

 simplest

0.87

oret

0.86

 latest

0.86

Activations Density 1.540%

references to specific dates or historical events

occurrences of the word "the."

No Comments

No Known Activations