INDEX

Explanations

quotations within the text

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, specifically quotation marks

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

 favor

-0.84

 grades

-0.80

 grade

-0.73

 catalog

-0.68

 rumored

-0.67

 vacation

-0.67

 honors

-0.67

 muse

-0.66

 scheduled

-0.65

 graded

-0.65

POSITIVE LOGITS

We

1.15

Firstly

1.14

Our

1.10

There

1.04

It

1.02

Therefore

0.99

Clearly

0.99

Quite

0.98

Such

0.98

Obviously

0.98

Activations Density 0.112%

quotations within the text

punctuation marks, specifically quotation marks

No Comments

No Known Activations