INDEX

Explanations

questions starting with the word "which"

oai_token-act-pair · gpt-3.5-turbo

typical sentence starters or phrases that introduce questions or topics

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ARC

-0.73

greg

-0.72

affle

-0.69

ancock

-0.68

ourning

-0.67

Rated

-0.67

usk

-0.65

perty

-0.65

ancial

-0.65

Repl

-0.64

POSITIVE LOGITS

 brings

1.52

 begs

1.51

 leads

1.26

 reminds

1.15

 means

1.15

 raises

1.12

 leaves

1.09

 explains

1.05

 translates

1.04

 makes

1.03

Activations Density 0.049%

questions starting with the word "which"

typical sentence starters or phrases that introduce questions or topics

No Comments

No Known Activations