INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific names in the text

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

enegger

-0.81

anwhile

-0.80

 referen

-0.69

 destro

-0.68

ä»£

-0.67

chnology

-0.63

ãĥ¼ãĥĨ

-0.60

raints

-0.60

ĸļ

-0.60

mble

-0.60

POSITIVE LOGITS

Coin

0.61

Forge

0.54

Day

0.53

Py

0.53

Hut

0.53

star

0.53

eland

0.53

 Temple

0.53

 Street

0.52

han

0.52

Activations Density 0.648%

proper nouns

proper nouns and specific names in the text

No Comments

No Known Activations