INDEX

Explanations

different ways of looking at or thinking about something

oai_token-act-pair · gpt-3.5-turbo

expressions related to different perspectives or approaches to understanding a situation

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

OTOS

-0.68

osponsors

-0.67

cover

-0.64

 ..............

-0.63

ikers

-0.62

 Provided

-0.61

 blockers

-0.60

][

-0.60

umerous

-0.59

éļ

-0.59

POSITIVE LOGITS

ety

0.72

aign

0.70

 fare

0.68

ilton

0.68

 structured

0.66

grass

0.63

phr

0.62

 interact

0.62

riage

0.61

ezvous

0.60

Activations Density 0.185%

different ways of looking at or thinking about something

expressions related to different perspectives or approaches to understanding a situation

No Comments

No Known Activations