INDEX

Explanations

adjectives related to different levels or variations of something

oai_token-act-pair · gpt-3.5-turbo

references to varying qualities or degrees of ownership

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

 Cobb

-0.65

MAP

-0.64

idav

-0.64

ertodd

-0.62

pta

-0.62

DIT

-0.62

 Marketable

-0.61

":""},{"

-0.61

agher

-0.60

ersen

-0.59

POSITIVE LOGITS

rio

0.83

 caliber

0.81

 renown

0.77

icial

0.77

 fame

0.77

 magnitude

0.76

il

0.76

 proportions

0.76

course

0.75

 utmost

0.75

Activations Density 0.303%

adjectives related to different levels or variations of something

references to varying qualities or degrees of ownership

No Comments

No Known Activations