INDEX

Explanations

text related to transparency or visibility, particularly using phrases containing "see-through" or "know-how"

oai_token-act-pair · gpt-3.5-turbo

suffixes and elements related to knowledge or expertise

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

ozo

-0.77

anchester

-0.73

iflower

-0.72

ccoli

-0.70

bably

-0.70

olicy

-0.70

odcast

-0.70

ulture

-0.69

emetery

-0.69

udeau

-0.67

POSITIVE LOGITS

ById

0.79

andum

0.79

opol

0.71

gat

0.70

marks

0.68

 Duty

0.67

vale

0.66

BIL

0.65

Quality

0.63

SEE

0.63

Activations Density 0.340%

text related to transparency or visibility, particularly using phrases containing "see-through" or "know-how"

suffixes and elements related to knowledge or expertise

No Comments

No Known Activations