INDEX

Explanations

phrases indicating events or actions

oai_token-act-pair · gpt-3.5-turbo

the use of the suffix "en."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 CASE

-0.61

 weekday

-0.58

quo

-0.55

 EVER

-0.54

 volts

-0.54

åĪ

-0.53

 happening

-0.52

 nationally

-0.52

ATL

-0.52

 Triple

-0.52

POSITIVE LOGITS

en

4.03

enic

2.08

eni

2.07

enf

2.05

ens

2.01

eny

1.97

EN

1.91

enes

1.87

eners

1.78

enh

1.76

Activations Density 0.032%

phrases indicating events or actions

the use of the suffix "en."

No Known Activations