INDEX

Explanations

negations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the absence or lack of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uzz

-0.82

 Volunte

-0.78

uns

-0.78

NI

-0.78

bis

-0.72

HAEL

-0.72

abee

-0.71

Alert

-0.71

Train

-0.70

SHARE

-0.69

POSITIVE LOGITS

 significance

1.36

 relevance

1.34

 meaning

1.26

 bearing

1.24

 validity

1.23

 implications

1.18

 resonance

1.14

 applic

1.11

 origins

1.10

 ramifications

1.10

Activations Density 0.164%

negations

phrases indicating the absence or lack of something

No Comments

No Known Activations