INDEX

Explanations

comparative statements indicating superiority

oai_token-act-pair · gpt-3.5-turbo

statements asserting superiority or preference

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

Py

-0.76

idon

-0.69

mad

-0.67

NH

-0.67

erity

-0.65

TRY

-0.64

FK

-0.63

psy

-0.61

aly

-0.61

Ber

-0.60

POSITIVE LOGITS

 suited

1.02

 than

0.95

 behaved

0.94

 acquainted

0.79

 manag

0.74

 cannabin

0.71

 quality

0.70

 lapt

0.68

than

0.68

 Than

0.68

Activations Density 0.034%

comparative statements indicating superiority

statements asserting superiority or preference

No Comments

No Known Activations