INDEX

Explanations

instances where a door is mentioned or involved

oai_token-act-pair · gpt-3.5-turbo

references to doors and their actions or states

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lihood

-0.81

ousand

-0.73

irtual

-0.71

arus

-0.70

utan

-0.69

ual

-0.68

ivia

-0.67

azeera

-0.67

OTAL

-0.66

 AMERICA

-0.65

POSITIVE LOGITS

bell

1.44

steps

1.35

frame

1.17

door

1.15

doors

1.13

ways

1.08

 doors

1.07

keeper

1.04

step

1.03

keepers

1.03

Activations Density 0.041%

instances where a door is mentioned or involved

references to doors and their actions or states

No Comments

No Known Activations