INDEX

Explanations

descriptions or qualities that are positively emphasized

oai_token-act-pair · gpt-3.5-turbo

phrases that describe a quality or feature of various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

"},"

-0.64

dies

-0.64

aths

-0.62

--+

-0.59

 glaciers

-0.58

 Figures

-0.58

this

-0.56

 segments

-0.55

iencies

-0.54

Topics

-0.53

POSITIVE LOGITS

 definitely

0.84

 VERY

0.83

 awfully

0.81

 absolutely

0.78

 ONLY

0.77

 HUGE

0.75

NOT

0.74

 gonna

0.74

 ours

0.73

 NEVER

0.72

Activations Density 0.317%

descriptions or qualities that are positively emphasized

phrases that describe a quality or feature of various subjects

No Comments

No Known Activations