INDEX

Explanations

numeric values in the input text

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĥ¼ãĥĨãĤ£

-0.60

 referen

-0.56

 Vaugh

-0.56

ãĥ¼ãĥĨ

-0.54

 disadvant

-0.49

edIn

-0.47

orno

-0.47

 Seym

-0.47

idated

-0.45

Kik

-0.45

POSITIVE LOGITS

taboola

0.61

NetMessage

0.59

 DRAGON

0.58

 DARK

0.52

SELECT

0.51

serv

0.46

BILITIES

0.46

OFF

0.46

gal

0.45

Activations Density 0.716%

numeric values in the input text

numerical data and statistics

No Comments

No Known Activations