INDEX

Explanations

proper nouns related to locations or people

oai_token-act-pair · gpt-3.5-turbo

common prefixes and suffixes in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĩ

-0.69

ī

-0.69

·

-0.68

 Citiz

-0.67

«

-0.67

orial

-0.65

İ

-0.65

ĺ

-0.65

OME

-0.64

lvl

-0.64

POSITIVE LOGITS

 infring

0.56

 spokeswoman

0.56

èĢħ

0.53

 accent

0.52

.—

0.52

.(

0.52

 contam

0.51

 spokesman

0.51

 arrives

0.50

!,

0.49

Activations Density 2.068%

proper nouns related to locations or people

common prefixes and suffixes in words

No Comments

No Known Activations