INDEX

Explanations

words related to the Olympics

oai_token-act-pair · gpt-3.5-turbo

mentions of the Olympic Games and related locations

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

TEXTURE

-0.70

 Bakr

-0.63

 penetrating

-0.61

xual

-0.59

 fitting

-0.59

vec

-0.59

FIELD

-0.58

 tongue

-0.56

Ã±o

-0.56

 corrections

-0.56

POSITIVE LOGITS

ics

1.27

ique

1.24

icism

1.22

icians

1.20

ications

1.15

ically

1.14

ic

1.14

ication

1.13

icate

1.12

icist

1.11

Activations Density 0.041%

words related to the Olympics

mentions of the Olympic Games and related locations

No Comments

No Known Activations