INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

repeated characters and patterns in words, emphasizing specific letters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

intosh

-0.72

eele

-0.72

akeru

-0.63

oppable

-0.62

tz

-0.62

 magnets

-0.60

 emoji

-0.59

alore

-0.57

 gears

-0.56

ItemTracker

-0.56

POSITIVE LOGITS

 corrid

0.75

 Swordsman

0.70

º

0.67

vest

0.62

ĺ

0.61

cript

0.60

ript

0.60

asp

0.59

ickey

0.58

 Lange

0.58

Activations Density 0.299%

proper nouns

repeated characters and patterns in words, emphasizing specific letters

No Comments

No Known Activations